CNN
-
Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model
2026-08-06 16:41:22Saad Ahmed, Md Khalid SyfullahaAbstract
Deaf and hard-of-hearing people in Bangladesh communicate mainly through Bangla Sign Language (BdSL). Automatic BdSL recognition on personal devices could widen access to education and services. Existing systems use controlled-setting datasets without expert verification and heavyweight pretrained backbones unsuited to on-device use. We introduce RSBdSL38, 10,874 expert-validated images spanning all 38 BdSL hand signs, representing the 51 letters of the Bangla alphabet, recorded from real signers at three special-needs schools across Bangladesh. We propose a lightweight attention based convolutional network of 298,470 parameters, built from grouped bottleneck residual blocks, channel and spatial attention, a multi-scale depthwise hand-feature block, dual pooling, and Swish activations. Trained from scratch, it attains 96.37% accuracy (95.72% +- 0.54% over five seeds), within 1.08 percentage points of the best of nine ImageNet-pretrained efficient architectures under an identical protocol, using 8.5 to 68x fewer parameters and 1.3 to 21.7x fewer MACs. Retrained, it reaches 92.95 to 98.33% on six public BdSL benchmarks, 97.04% on a merged corpus, and 76.25% zero-shot on BdSL-38. Removing any architectural stage costs 7.61 to 89.30 points, against at most 3.17 for the training recipe. Grad-CAM with deletion-insertion and weight-randomization checks confirms that predictions follow the signing hand. A signer-independent split holding out 6 of 36 signers yields 85.18%. Quantized to 0.48 MB, it runs at 3.98 ms per image within a 15.5 MB footprint on a commodity smartphone. Together, RSBdSL38 and our from-scratch model turn benchmark accuracy into deployable accessibility at a fraction of pretrained-backbone cost; dataset, code, and models are released.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06252
PDF
-
Integrating Implicit and Explicit Relational Biases through Graph-Based Multiple Instance Learning: A Case Study in Skin Lesion Diagnosis
2026-08-06 13:47:18Rafa{\l} Buler (Gda\'nsk University of Technology), Jakub Buler (Gda\'nsk University of Technology), Maciej Bobowicz (Medical University of Gda\'nsk), Micha{\l} Grochowski (Gda\'nsk University of Technology)Abstract
Relational inductive biases are essential for capturing structural dependencies among data. This study investigates a dual-level relational framework for image classification, bridging the gap between implicit representation learning and explicit structural modelling. We begin by establishing a baseline using an EfficientNetB3 architecture. To move beyond standard convolutional biases, we adopt a patch-based strategy, employing a convolutional masked autoencoder to learn implicit inter-patch relationships through self-supervised reconstruction. We then extend this approach by incorporating explicit relational modelling, organizing the learned embeddings into various graph topologies, including grid-based, random, and k-nearest neighbour structures. Experimental results on the ISIC-2018 and ISIC-2019 skin lesion diagnosis benchmarks show that combining implicit inter-patch modelling with explicit graph-based message passing yields the best performance. On the ISIC-2018 test set, the baseline model achieves a balanced accuracy of 76.17%, which improves to 77.12% with implicit patch-based relational modelling. The fully integrated grid-structured Graph Attention Network further increases performance to 79.27%. Similarly, on ISIC-2019, the implicit approach reaches 59.84% balanced accuracy, while the combination of implicit and explicit modelling yields 60.67%.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06037
PDF
-
Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation
2026-08-06 10:17:23Th\'eo Danielou, Antoine Saporta, L\'eo Alberge, Corentin DancetteAbstract
Radiology foundation models learn transferable representations that can be adapted to new tasks by training only small layers on top of a frozen encoder. Dense prediction tasks such as 3D segmentation are, however, underrepresented in their evaluation, and, with the encoder kept frozen, pre-trained models still fall short of nnU-Net, the state-of-the-art reference trained from scratch. To close this gap we extend convolutional MAE pre-training with a robust reconstruction objective, a feature regularizer, and a local-global similarity objective. Using this method, we propose Curia-MAE, a multi-modal, multi-anatomy MAE model pre-trained on 300,000 CT and MRI images covering a large number of anatomical sites. On eight anatomy- and lesion-focused segmentation benchmarks, Curia-MAE improves frozen-encoder performance over a strong MAE baseline, while remaining competitive under full finetuning and superior on lesion tasks, where labeled data is scarce. These results indicate that a single frozen encoder can be reused across diverse segmentation tasks, reducing the cost of adapting and deploying such models in clinical workflows. We will make our pre-trained model weights publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05844
PDF
-
LILAC: An Idempotent Neural Speech Codec
2026-08-06 08:09:48June Young Yi, Dongwook Lee, Jiheum Yeom, Sungroh YoonAbstract
Neural Audio Codecs are widely adopted in speech generation and editing. However, existing neural audio codecs are not idempotent: across the paper's twelve baseline systems, every configuration tested rewrites, on average, at least 15% of its tokens in a single decode-re-encode pass. This poses a problem for utilizing Neural Audio Codecs as token interfaces in pipelines where re-encoding decoded outputs can occur. We present LILAC, a fully convolutional 24 kHz speech codec at 9.375 Hz and 0.75 kbit/s that is codec idempotent by construction; re-encoding the decoded audio of any valid token stream returns the identical stream. LILAC achieves idempotency while maintaining competitive quality, reaching UTMOS 4.14 and 4.24 on LibriSpeech and LibriTTS-R test sets, comparable to SOTA sub-1 kbit/s Neural Audio Codecs.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05727
PDF
-
Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI
2026-08-05 16:36:06Casey Wall, Longwei Wang, Rodrigue Rizk, KC SantoshAbstract
Gradient-weighted Class Activation Mapping (Grad-CAM) is widely used to visualize model decisions, but it was originally formulated for convolutional neural networks, where spatial feature maps and channel dimensions have clear architectural meanings. Vision Transformers (ViTs) do not provide the same structure, instead representing images through tokens, attention, residual streams, and multimodal interactions. This paper presents a systematic taxonomy and literature audit of how Grad-CAM and related methods are adapted, justified, and reported for ViT-based architectures. From an initial search of more than 550 papers, we identify 175 papers that apply Grad-CAM or Grad-CAM-adjacent methods to ViTs. We find that most papers do not provide a full mathematical or implementation-level account of how Grad-CAM is adapted to transformer representations. To characterize this gap, we introduce a descriptive taxonomy of ViT Grad-CAM adaptations that makes explicit the feature locations, gradient targets, spatial reconstruction steps, and aggregation choices that are often left implicit. This taxonomy is not intended to prescribe a single correct adaptation, but to clarify the range of methodological choices being made. The study shows that Grad-CAM on ViTs is often treated as a trivial extension of CNN-based Grad-CAM, despite requiring nontrivial choices that affect rigor, reproducibility, and interpretation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05258
PDF
-
A 6G Integrated Sensing and Communication Framework for Railway Intrusion Detection and Collision Prediction
2026-08-05 11:24:03Ajeet Kumar Yadav, Sankaran Balasubramaniam, Aritra Chatterjee, Vinod Aduru, Yogesh Simmhan, Pandarasamy ArjunanAbstract
Integrated Sensing and Communication (ISAC) combines sensing and communication to efficiently utilize wireless resources and is emerging as a key paradigm for next-generation wireless networks. By leveraging the wide bandwidth, high frequencies, and massive antenna arrays of 5G-Advanced and 6G systems, ISAC enables physical-layer sensing using Channel State Information (CSI). The 3rd Generation Partnership Project (3GPP) Release 19 identifies 32 potential ISAC use cases, with particular emphasis on detecting and tracking moving objects. In this work, we address the Sensing for Railway Intrusion Detection use case, where intruders, including wildlife, entering a railway track can pose serious collision risks. We generated 22,695 CSI matrices with corresponding ground truth using a 3D-rendered railway environment and the Sionna radio simulator. We developed a machine learning model combining a three-dimensional Convolutional Neural Network (3D CNN) and Bidirectional Long Short-Term Memory (BiLSTM) network to detect intruders in the track danger zone and estimate their real-time position relative to the train, velocity, and time to collision. On synthetic CSI data, the model achieves 99.57% intruder-detection accuracy on a balanced test set and a combined Mean Absolute Error (MAE) of 0.4240 for position, velocity, and time-to-collision prediction. These results demonstrate the potential of CSI-based ISAC sensing with machine learning for reliable railway intrusion detection. The complete codebase for CSI generation, preprocessing, and model development is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04710
PDF
-
GASP: GPU-Accelerated Safe Planner for Real-Time Collision-Aware Motion Generation with Latent Trajectory Sampling
2026-08-05 09:18:16Colin Merk, Stefanos Charalambous, Peter D\"urr, Farshad KhadivarAbstract
We present GASP, a GPU-Accelerated Safe Planner for real-time, collision-aware joint-space motion generation in known environments. GASP combines a clamped B-spline trajectory parameterization with a convolutional residual neural network that predicts the free interior control points, while analytically inserted boundary control points enforce initial and final derivative constraints for collision-aware planning under non-stationary conditions. A conditional variational autoencoder samples multiple trajectory candidates, which are decoded and validated in parallel on the GPU, yielding a batched planner for collision-aware coupled joint-space motion with near-millisecond inference. We validate GASP as an online motion-generation module, where it achieves analytical-level success rates with high collision-aware feasibility and substantially reduces inference time relative to GPU-based trajectory optimization. We further deploy GASP as a reinforcement-learning reset planner in competitive robotic table tennis, matching the baseline return rate while roughly halving training-time collisions.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04612
PDF
-
Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection
2026-08-05 08:11:07Kadir-Kaan \"Ozer, Ren\'e Ebeling, Markus EnzweilerAbstract
Time series anomaly detectors have grown steadily more complex, incorporating attention mechanisms, adversarial training, and stochastic latent variables. Yet, it is unclear how much of this machinery detection actually requires. We test this question with JuRe (Just Repair), a deliberately minimal detector: a single depthwise-separable convolutional residual block trained to repair Gaussian-corrupted, channel-masked windows, scored at inference by a fixed structural discrepancy function with no learned parameters. JuRe ranks second on the TSB-AD multivariate benchmark (AUC-PR 0.404 over 180 series) and second on the UCR univariate archive (AUC-PR 0.201 over 250 series), where it leads all neural baselines. On TSB-AD, JuRe runs roughly $20\times$ faster than AxonAD, one of the top-ranked methods on that benchmark. Full-benchmark ablations show that removing Gaussian corruption reduces AUC-PR by 0.046, whereas AUC-PR across the evaluated architecture variants spans at most 0.017. A synthetic linear-manifold experiment provides partial evidence for this geometric interpretation: anomaly scores correlate with true off-manifold distance (Pearson $r=0.725$), and repair directions align increasingly with the true projection as anomaly magnitude grows. Wilcoxon signed-rank tests with Holm correction find significant differences against 20 of 25 baselines, although dependence among series limits dataset-level interpretation. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.17388
PDF
-
Predictive Failure Detection in Network Hardware Using Thermal Imaging and Deep Learning with Sensor Fusion
2026-08-05 04:32:30Ashly JosephAbstract
Unplanned network hardware malfunctions can interrupt services and result in expensive downtime in data centers. A deep learning-based predictive maintenance strategy is presented that utilizes thermal imaging and power sensor data to detect early indicators of equipment breakdown in routers, switches, and servers. A simulated dataset was generated comprising annotated thermal pictures and power readings indicative of three operating states: Normal, Warning, and Critical. Three ImageNet-pretrained convolutional neural network (CNN) models ResNet-50, InceptionV3, and VGG16 were assessed together with a multi-modal CNN-LSTM fusion model that integrates visual and sensor time-series information. Experiments were performed with and without pre-processing procedures, including region-of-interest (ROI) extraction and normalization. In the absence of pre-processing, CNNs attained moderate accuracy (e.g., ResNet-50 at 52%), but ROI-based pre-processing significantly enhanced performance (ResNet-50 accuracy reaching 91%). The CNN-LSTM model attained the greatest accuracy of 94%, with precision and recall approaching 95%, illustrating the effectiveness of multi-modal fusion. The results validate that domain-specific pre-processing and sensor fusion substantially improve early failure prediction, providing a potential foundation for proactive maintenance of network hardware through non-intrusive monitoring.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07582
PDF
-
Image Classification Using CNN-QNN Hybrid Model with Optimized Correlated Features
2026-08-05 02:39:03Minseo Seong, Youngwook KimAbstract
We propose a method to optimize the correlation among convolutional neural network (CNN) features that are used as inputs to quantum neural network (QNN) to enhance image classification accuracy. Unlike prior approaches that employ orthogonal decomposition as preprocessing, we intentionally introduce correlated features that are more physically compatible with QNN. This design leverages the QNN's inherent ability to exploit quantum entanglement for representing correlated states-an advantage unavailable to classical neural networks. We hypothesize that aligning feature correlations with the entanglement structure of QNN improves binary classification performance. Based on a mathematical derivation of QNN outputs, Monte Carlo simulations indicate that an average correlation between features of 0.5 yields optimal classification accuracy. To validate this finding, we evaluate a quantum-classical hybrid model on three tasks: CIFAR-10 (automobile vs. truck), Fashion-MNIST (shirt vs. coat), and radar micro-Doppler signatures (robotic dogs vs. non-robots). To regulate feature correlations, we introduce a correlation-regularization term on the outputs of the CNN, driving the off-diagonal entries of the feature correlation matrix toward a target constant. Across all datasets, inducing intermediate correlation consistently improved accuracy compared to low, high, or unregulated correlations, while also reducing classification accuracy variance. These results demonstrate that imposing moderate feature correlations-without modifying the quantum circuit-enhances classification accuracy and stability by aligning feature statistics with the QNN's entanglement structure. This study highlights the potential of QNN to surpass the performance of classical classifiers as more qubits become available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04379
PDF
-
Beyond Isotropic Assumptions: Continuity-Constrained Segmentation and GPU Morphometry for Nanoscale GBM Analysis
2026-08-04 18:28:19Arash Fatehi, Robin Ebbestad, Linus Butt, Hans Blom, Sigrid Lundberg, Hannes Olauson, Hjalmar Brismar, David Unnersj\"o-Jess, Thomas Benzing, Katarzyna BozekAbstract
Confocal microscopy of optically cleared and swelled tissue resolves complex biological structures in 3D, but such acquisitions are highly anisotropic: along the under-sampled axial direction the structure can appear discontinuous, hampering reconstruction and automated quantitative analysis. The usual remedy upsamples the axial dimension to an isotropic volume before training a segmentation model, which requires dense annotations in the upsampled space, a prohibitive labeling burden. We present an end-to-end, GPU-accelerated framework that overcomes this without additional annotations. The model is trained on the native acquisition volume; random rotation of training patches leverages the well-resolved lateral plane to supply the missing axial information, and a z-axis continuity loss keeps neighboring slices consistent. We adapt both a convolutional (3D U-Net) and a transformer (SwinUNETR) backbone, aggregate overlapping patches by Gaussian consensus, and compute point-spread-function-corrected membrane thickness by ray-surface intersection on the GPU. We apply the method to the glomerular basement membrane (GBM), a thin, highly convoluted part of the kidney's filtration barrier that grows more irregular in disease. Segmentation accuracy matches inter-expert agreement. Continuity-aware training improves reconstruction smoothness and suppresses a periodic terracing artifact at minimal accuracy cost. We quantify GBM thickness across the reconstructed 3D surface and capture disease-related thickening, enabling fully automated anisotropic 3D morphometry of biological structures without dense volumetric labels or image restoration.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07575
PDF
-
Deep Learning for Real-Time Sound Order Recognition in Human-Robot Interaction
2026-08-04 15:54:26Rezaul Tutul, Usaid Khan, Andre Jakob, Ilona BuchemAbstract
Recognizing the temporal order of overlapping sounds is an underexplored challenge in human-robot interaction (HRI), with direct relevance to applications such as first responder detection systems. This paper presents a deep learning framework for real-time sound order recognition using recordable buzzers that emit distinct non-verbal sounds (cat meows, dog barks, helicopter noises). A multi-branch convolutional neural network (CNN) processes Mel spectrograms, Mel-frequency cepstral coefficients (MFCCs), and short-time Fourier transform (STFT) features, with an attention-based fusion mechanism to emphasize critical temporal cues. Experiments were conducted under same-amplitude, varied-amplitude, and unseen sound conditions. The proposed system achieved 99% accuracy in balanced overlaps, 91% under amplitude variation, and 74% on unseen test data with normalization. These results demonstrate that deep learning can reliably recognize sound order in overlapping conditions, supporting practical HRI scenarios. While experiments were conducted on carefully controlled synthetic overlaps, we additionally report latency benchmarks demonstrating real-time feasibility and provide an extended discussion on generalization, ecological validity, and deployment challenges in real-room environments.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04072
PDF
-
Towards Reliable and Reproducible Fetal Brain Biometry: A Deep Learning Approach Using MRI
2026-08-04 14:20:40Francesca Maccarone, Marina Di Stefano, Giorgio Longari, Giulia Frigerio, Gloria Rizzato, Rocco Prudentino, Nivedita Agarwal, Tommaso Ciceri, Denis Peruzzo, Simone MelziAbstract
Fetal brain biometry is essential for quantitative assessment of brain development, supporting gestational age estimation, developmental monitoring, and detection of abnormalities. In clinical practice, measurements are manually performed, making them time-consuming and prone to variability. While automated approaches have been proposed, reproducible methods remain limited, particularly those providing anatomically interpretable landmark localization. We present a fully automated deep learning-based framework for reliable and reproducible brain biometry from 3D super-resolution-reconstructed fetal brain MRI. The proposed four-step pipeline derives biometric parameters by jointly estimating linear measurements and their corresponding anatomical landmarks. A 3D convolutional neural network is trained to regress landmark coordinates from brain segmentation label maps, followed by measurement-specific geometric optimization to refine landmark positions and compute measurements. The pipeline is evaluated on two publicly available fetal MRI datasets comprising 150 volumes (gestational age range: 20-37 weeks) acquired across different scanners and protocols, assessing five key biometric measurements across varying acquisition settings and providing a comprehensive evaluation of both measurement accuracy and landmark localization using quantitative metrics and visual assessment. Compared with the only available automated pipeline, the proposed method achieves comparable or improved accuracy for most measurements. In conclusion, we introduce a straightforward pipeline for reliable biometry estimations, with efficiency, interpretability and scalability that support integration into clinical workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03724
PDF
-
Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity
2026-08-04 06:54:29Chinmoy Mitra, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Rakibul Islam, M. F. MridhaAbstract
Federated learning (FL) enables aircraft fleet operators to jointly train remaining-useful-life (RUL) models from engine sensor telemetry without sharing raw data. This study examines two complementary challenges: benign heterogeneity, where honest operators observe different operating conditions and fault modes, and adversarial heterogeneity, where compromised operators submit poisoned updates. We conduct a controlled, safety-oriented evaluation using a multi-task one-dimensional convolutional neural network and a structurally non-IID partition of the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) benchmark. We compare four remedies for benign heterogeneity and evaluate five attacks against four aggregation methods, including a physically motivated sensor-value backdoor designed to mask engine degradation. Shared-representation personalization closes approximately 70% of the local-to-centralized root-mean-square-error gap, compared with 21% for proximal regularization and 10% for server-side reweighting. The backdoor achieves a 94.9% attack success rate against standard averaging while leaving clean accuracy statistically unchanged, demonstrating that accuracy alone cannot certify model safety and that attack success must be evaluated explicitly. Krum reduces attack success by an order of magnitude and is the only evaluated aggregator that withstands coordinated attackers, whereas personalization alone provides no protection. Combining personalization with robust aggregation restores robustness (2.8% attack success) with only a small accuracy cost, revealing a trade-off between robust update selection and collaborative representation learning. Results remain consistent across client counts and on a harder six-condition dataset. Code and data partitions are released for reproducibility.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04045
PDF
-
SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding
2026-08-04 05:52:17Wei Song, Yuxin Cao, Zhenchang Xing, Liming Zhu, Jin Song Dong, Yulei Sui, Jingling XueAbstract
Invisible image watermarks are increasingly used for deepfake detection and provenance tracking, where they must survive not only incidental distortions but also deliberate removal. We revisit spread-spectrum embedding, a classical watermarking principle, inside a modern neural post-hoc watermarking architecture. Our starting point is a measurement: in existing encoder-decoder schemes each message bit occupies only a small fraction of the image, a shared contributing factor to their fragility, since removal then need only disturb the region a bit occupies. SpreadMark instead spreads each bit as a dense pseudo-random codeword over the whole image and recovers it by matched-filtering a learned cover-suppressed chip representation, with a parallel convolutional decoding path and sparsification-aware training. A conditional chip-space analysis shows that, under a codeword-independent perturbation model, dense spreading increases the budget required to disrupt matched-filter recovery. Evaluated on COCO and DIV2K against nine schemes, SpreadMark is the only evaluated method retaining high detection under both the regeneration and the latent-space sparsification settings we test, with competitive JPEG and additive-noise robustness. It keeps the embedded watermark imperceptible, maintaining high perceptual quality on both COCO and DIV2K.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03165
PDF
-
UAV-Based Environmental Monitoring of Rip-Current Indicators Using Wavelet-Derived Texture Features
2026-08-03 16:24:05Yonatan Ben Avraham, Baruch Binyaminov, Yehudit ApersteinAbstract
Rip currents are recurrent coastal natural hazards that threaten beachgoers and create operational challenges for lifeguards and coastal managers. Reliable monitoring from standard RGB (red-green-blue) imagery acquired by unmanned aerial vehicles (UAVs) remains difficult because hazardous channels often appear as subtle gaps in breaking waves, foam texture, or sediment patterns, and these signatures are affected by illumination, sea state, and environmental noise. This study presents a physically informed coastal environmental monitoring workflow for detecting visually expressed rip-current indicators that integrates wavelet-derived spatial-frequency texture features with deep learning. We evaluate multiple strategies for incorporating Discrete Wavelet Transform features into convolutional architectures, from computationally efficient channel replacement to dual-stream fusion with attention mechanisms. Performance is assessed against a standard RGB baseline using a task specific convolutional neural network for image-level presence classification and a YOLOv8 model for object-level localization. Under the evaluated dataset conditions, integrating wavelet derived texture features improves performance over RGB-only models. The dual-stream architecture achieves the strongest classification performance, exceeding 95% accuracy with high recall, while channel replacement is most effective for YOLOv8 object detection, reaching 94% mAP@50 for localization. Explainable artificial intelligence analyses provide qualitative evidence that the models attend to visually plausible wave-gap regions associated with rip currents. These results suggest that under the conditions of the evaluated dataset, physically informed wavelet integration may support UAV-based decision-support tools for interpretable beach-safety risk mitigation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02448
PDF
-
Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs
2026-08-03 15:39:36Sathiyamohan Nishankar, Nethmi Pathirana, Pubudu Sanjeewani, Asanka Perera, Selvarajah ThuseethanAbstract
Most evidence on the effectiveness of explainable artificial intelligence (XAI) attribution methods has been established on convolutional neural networks (CNNs), with limited investigation into whether these conclusions generalize to the diverse Vision Transformer (ViT) architectures that now dominate computer vision. This paper presents a controlled benchmark that evaluates attribution quality across five dimensions: faithfulness, localization, robustness, complexity, and computational cost. A standardized framework assesses 13 attribution methods from four algorithmic families on eight representative backbones spanning CNNs, isotropic ViTs, hierarchical transformers, hybrid architectures, and linear-attention transformers. The results show that attribution performance is strongly architecture-dependent and that rankings established on CNNs do not reliably transfer to transformer-based models. CAM-based methods achieve the highest scores under the conventional bounding-box localization metric on CNNs and most ViTs but perform poorly on linear-attention architectures. Pixel-level dense-mask evaluation further reveals that these gains largely reflect metric saturation rather than accurate localization. CAM-based methods also exhibit limited robustness on global-attention transformers, whereas attention rollout provides consistently stable explanations with poor localization. Furthermore, faithfulness correlation offers limited discrimination between attribution methods, highlighting the limitations of single-metric evaluation. These findings challenge prevailing conclusions on attribution performance and demonstrate the need for architecture-aware, multi-dimensional evaluation. The open-source code for the evaluation framework and benchmark results is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02396
PDF
-
SWINSleepNet: A Hierarchical Context-Aware Framework for Sleep Staging
2026-08-03 13:07:49Chongjian Wang, Junjie GaoAbstract
Automatic sleep staging is a critical role in sleep disorder diagnosis, sleep quality assessment, and long-term health monitoring; however, existing approaches suffer poor performance on ambiguous and transition-related sleep stages, caused by inadequate modeling of fine-grained intra-epoch structures and complex cross-region spectral dependencies. Traditional epoch-level encoders commonly fail to extract subtle temporal microstructures and intra-epoch cross-region interactions, resulting in unsatisfactory recognition accuracy for hard categories such as the N1 stage. To tackle these drawbacks, we propose SwinSleepNet, a hierarchical context-aware dual-stream framework that separately optimizes intra-epoch representation learning and inter-epoch contextual modeling. Concretely, we characterize each sleep epoch from two complementary perspectives: raw time-domain EEG signal and its time-frequency transformation. The time-domain branch adopts convolutional encoders to capture fine waveform temporal details, and the time-frequency branch uses Swin Transformer to extract local spectro-temporal features, hierarchical multi-scale information and long-range spatial dependencies. The multi-branch extracted features are fused into integrated embeddings, which are optimized by a bidirectional context module to capture cross-epoch temporal dependencies for final sleep stage classification. Comprehensive experiments on Sleep-EDF-20, Sleep-EDF-78 and SHHS datasets verify that our method achieves competitive overall performance, and exhibits stronger robustness and stability on difficult N1 stages and transitional epochs. The results prove that optimized intra-epoch representation learning based on hierarchical architecture greatly benefits automatic sleep staging tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02183
PDF
-
HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams
2026-08-03 12:28:11Shivani Mall, Swarnim Jain, Joao F. HenriquesAbstract
Much of the recent progress in image and video recognition has come at the cost of memory: larger models, increased resolution, and longer temporal contexts. An inevitable component is the quadratic (or larger) growth of memory and compute based on image resolution, which is a property of the grid sampling used in convolutional networks and vision transformers. In this work we study residual networks whose convolutional blocks have logarithmic-square growth instead, enabling them to process very high-resolution video quickly. The key insight is to use a residual architecture's residual stream as a high-resolution buffer, to which convolutional blocks only read and write via log-polar image warp operations. Layers adaptively focus on different parts of each frame, with very high resolution only near the focus point. A complete high-resolution representation is built up in the residual stream, analogous to eye saccades creating a complete picture in biological vision, and a theoretical construction is presented that eliminates the quadratic dependency of the residual stream resolution. Experiments demonstrate that our proposed HiResNets learn to foveate around scenes similarly to human vision, and have superior performance in difficult egocentric video recognition tasks, especially egocentric video with small objects and fine-grained recognition.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02140
PDF
-
TBSG-Net: Temporal Bipartite Scene Graph Network for Fine-Grained Video Moment Retrieval
2026-08-03 10:52:32Ji Huang, Yongsheng Dai, Tianyu Ren, Barry Devereux, Hui WangAbstract
Recent advances in proposal-free Video Moment Retrieval (VMR) have highlighted the effectiveness of Static Scene Graphs (SSGs). By modeling objects and their relations at the frame level, SSGs enrich retrieval-oriented video representations. However, integrating SSGs into VMR remains constrained by two inherent limitations: (1) Lack of Temporal Dynamics. SSGs fail to model how objects and their relationships evolve over time, leading to the loss of essential temporal dependencies in video representation; and (2) Lack of Explicit Temporal Span Encoding. SSGs do not explicitly encode the duration of relationships, making precise localization challenging. To address these limitations, we propose Temporal Bipartite Scene Graph Network (TBSG-Net)---to the best of our knowledge, the first Dynamic Scene Graph (DSG) based proposal-free VMR model. Specifically, TBSG-Net leverages DSGs to extract event-centric graph representations of the input video, enabling the modeling of object interactions over time and thus addressing limitation (1). These DSGs are then processed by a novel Dynamic Scene Graph Embedding (DSG-E) module to capture both Temporal Span and spatio-temporal information. First, DSG-E utilizes a TBSG Constructor to transform DSGs into TBSGs, explicitly encoding objects, relationships, and time spans to tackle limitation (2). Second, the resultant TBSGs are passed into a hybrid TBSG Encoder that integrates a Transformer variant for global event modeling and a Graph Convolutional Network for detailed relational reasoning, ultimately producing a more comprehensive spatio-temporal representation. Our experiments demonstrate substantial improvements of TBSG-Net over all baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02056
PDF
