Contour
-
BRIDGE: Background Routing and Isolated Discrete Gating for Coarse-Mask Local Editing
2026-05-08 15:09:11Peilin Xiong, Honghui Yuan, Junwen Chen, Keiji YanaiAbstract
Coarse-mask local image editing asks a model to modify a user-indicated region while preserving the surrounding scene. In practice, however, rough masks often become unintended shape priors: instead of serving as flexible edit support, the mask can pull the generated object toward its accidental boundary. We study this failure as mask-shape bias and frame the task through a Two-Zone Constraint, where the background should remain stable while the editable region should follow the instruction without being forced to inherit the mask contour. BRIDGE addresses this setting by keeping masks outside the DiT backbone for support construction and blending, avoiding DiT-internal mask injection and copied control branches. It uses BridgePath generation, where a Main Path preserves background context and a Subject Path generates editable content from independent noise. Motivated by a diagnostic Qwen-Image experiment showing that positional embeddings and attention connectivity regulate which image context visual tokens reuse, BRIDGE introduces a learnable Discrete Geometric Gate for token-level positional-embedding routing. This gate lets subject tokens borrow background-anchored coordinates near fusion regions or keep subject-centric coordinates for geometric freedom. We evaluate BRIDGE on BRIDGE-Bench, MagicBrush, and ICE-Bench. On BRIDGE-Bench, BRIDGE improves Local SigLIP2-T from 0.262 with FLUX.1-Fill and 0.390 with ACE++ to 0.503, with parallel gains in local DINO and DreamSim. Zero-shot results on MagicBrush and ICE-Bench further indicate competitive alignment and source preservation beyond the curated benchmark, while the added routing module remains compact at 13.31M parameters compared with ControlNet-style copied branches.
Abstract (translated)
URL
https://arxiv.org/abs/2605.07846
PDF
-
What Cohort INRs Encode and Where to Freeze Them
2026-05-08 11:09:30Vasiliki Sideri-Lampretsa, Sophie Starck, Robbie Holland, Julian McGinnis, Daniel RueckertAbstract
Reusing the early layers of cohort-trained INRs as initialization for new signals has been shown to accelerate and improve signal fitting, yet it remains unclear which layers of the shared encoder learn transferable representations and what those representations encode. We address both questions for two standard backbones, SIREN and Fourier-feature MLPs (FFMLP). First, sweeping the freeze depth across the shared encoder at test time, we find that the optimum coincides with the layer of highest weight stable rank. Moreover, freezing at this depth matches or improves on the standard fine-tuning recipe across all our experiments. Second, identifying which layer transfers does not characterize what that layer encodes. To address this we adopt sparse autoencoders (SAEs), the dominant tool in mechanistic interpretability, and present the first SAE decomposition of INR activations into sparse dictionary atoms. Interestingly, SIREN and FFMLP achieve comparable cohort-fitting quality, but learn qualitatively different dictionaries. Cohort SIREN's atoms are localized, tiling the coordinate plane such that each atom fires in a confined region independent of cohort content. Cohort FFMLP's atoms are image-spanning, tracing the contours of memorized cohort signals. Single-atom ablations confirm causal use of these dictionaries: a single FFMLP atom out of 4096 can drop PSNR by up to 10.6 dB across the image, while SIREN ablations remain confined to where the atom fires. Together, these results give the first mechanistic account of what transfers in cohort-trained INRs and turn their activations into inspectable dictionary atoms. These tools open a path towards characterizing what INRs encode and towards architectures designed for generalization rather than memorization.
Abstract (translated)
URL
https://arxiv.org/abs/2605.08298
PDF
-
Anatomical Landmark-Guided Deep Reinforcement Learning for Autonomous Gastric Navigation
2026-05-08 03:11:21Haoxuan Wu, Sishen Yuan, Haitao Gao, Zhen Li, Xiuli Zuo, Hongliang RenAbstract
Wireless capsule endoscopy (WCE) enables painless visualization of the gastrointestinal tract, but its diagnostic potential is limited by incomplete mucosal coverage and poor transferability of existing navigation methods across patient anatomies. We propose a transferable, anatomical landmarkguided deep reinforcement learning (AL-DRL) framework for autonomous gastric navigation. Leveraging a lightweight edgecontour-depth fusion module, our policy operates on stable, lowdimensional landmark coordinates rather than high-dimensional video streams, effectively bridging the sim-to-real gap. In simulations across eight patient-derived models, the method achieves over 97% coverage within 50 seconds, significantly outperforming vanilla PPO, SAC, and DQN agents. A two-stage sim-to-real pipeline with an adaptive dynamic programming controller actively mitigates physical disturbances. Ex-vivo experiments demonstrate a mean coverage of 87% and a 53% reduction in procedure time compared with expert manual control.
Abstract (translated)
URL
https://arxiv.org/abs/2605.08269
PDF
-
Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding
2026-05-08 02:20:40Yuan Yao, Qiushi Yang, Humen Zhong, Jiangning Wei, Yifang Men, Shuai Bai, Miaomiao Cui, Zhibo YangAbstract
Open-world referring segmentation requires grounding unconstrained language expressions to precise pixel-level regions. Existing multimodal large language models (MLLMs) exhibit strong open-world visual grounding, but their outputs remain limited to sparse bounding-box coordinates and are insufficient for dense visual prediction. Recent MLLM-based segmentation methods either directly predict sparse contour coordinates, struggling to reconstruct continuous object boundaries, or rely on external segmentation foundation models such as the Segment Anything Model (SAM), introducing substantial architectural and deployment overhead. We present Qwen3-VL-Seg, a parameter-efficient framework that treats the MLLM-predicted box as a semantically grounded structural prior and decodes it into pixel-level referring segmentation. At its core, a lightweight box-guided mask decoder combines multi-scale spatial feature injection, spatial-semantic query construction, box-guided high-resolution pixel fusion, and iterative mask-aware query refinement, introducing only 17M parameters (about 0.4\% of the base model). For scalable open-world training, we construct SA1B-ORS, an SA-1B-derived dataset with two subsets: SA1B-CoRS (category-oriented samples) and SA1B-DeRS (descriptive, instance-specific samples). For evaluation, we curate ORS-Bench, a manually screened benchmark with in-distribution and out-of-distribution subsets covering diverse referring expression types. Extensive experiments on referring expression segmentation, visual grounding, and ORS-Bench show that Qwen3-VL-Seg performs strongly across closed-set and open-world settings, with clear advantages on language-intensive instructions and strong out-of-distribution generalization. Evaluations on general multimodal benchmarks further show that the model broadly preserves general-purpose multimodal competence after segmentation-oriented adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2605.07141
PDF
-
Overcoming data scarcity through multi-center federated learning for organs-at-risk segmentation in pediatric upper abdominal radiotherapy
2026-05-07 18:21:43Mianyong Ding, Maximilian Knoll, Semi Harrabi, Martine van Grotel, Annemieke S. Littooij, Max van Noesel, Jens-Peter Schenk, Marry M. van den Heuvel-Eibrink, Geert O. Janssens, Matteo MasperoAbstract
Deep learning-based organs/structures-at-risk(OARs) auto-contouring models can improve radiotherapy workflows, but models trained on adult data often underperform in pediatric patients. Developing robust pediatric-specific models is hindered by data scarcity and fragmentation across centers. Federated learning (FL) enables privacy-preserving collaborative training without the need for data sharing. We evaluated the feasibility and performance of FL for developing pediatric-specific OAR segmentation models across two European medical centers. Computed tomography (CT) images from pediatric patients from Utrecht and Heidelberg with a renal tumor or abdominal neuroblastoma were retrospectively collected and locally processed. An nnU-Net-based framework segmented 19 OARs using local and FL schemes. FL was implemented with secure weight exchange on a cloud storage across institutional firewalls. Performance was assessed using the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance, and mean surface distance. Robustness to patient orientation, false-positive segmentation of surgically removed kidneys, and failure cases were identified. A total of 310 postoperative CTs from 272 patients (105 renal tumors, 167 neuroblastomas) were included. Local models performed well on their respective center data but showed significantly reduced cross-center performance for four to seven of the nine evaluated OARs (DSC). In contrast, the FL model matched local performance for at least seven of nine OARs and achieved the best cross-center results across three metrics, with DSC gains of 0.003-0.007 over local models. FL also maintained stable performance across patient orientations and reduced false-positive kidney segmentations. Real-world FL improves cross-center robustness of CT-based OAR segmentation models in pediatric upper abdominal tumors.
Abstract (translated)
URL
https://arxiv.org/abs/2605.06820
PDF
-
Accurate Trajectory Tracking with MPCC for Flapping-Wing MAVs
2026-05-07 11:31:34Charbel Toumieh, Jack Zeng, Niel Mistry, Dario FloreanoAbstract
Flapping-wing micro aerial vehicles offer quieter and safer operation than rotary-wing drones, yet achieving precise autonomous control of bird-scale ornithopters remains challenging: lift, airspeed, and turning authority are tightly coupled and governed by only a few control inputs. Conventional cascaded controllers treat altitude, speed, and heading independently, producing persistent tracking errors during complex maneuvers, while time-parameterized trajectory tracking requires predefined speed profiles that existing methods cannot robustly produce for these coupled dynamics. We address both limitations simultaneously with a Model Predictive Contouring Control (MPCC) approach that tracks arc-length-parameterized trajectories while optimizing progress online, eliminating the need for predefined timing. However, MPCC requires a dynamical model that captures the coupled aerodynamics without exceeding the computational budget of real-time nonlinear optimization. Here, we propose a compact, continuously differentiable model that captures the dominant couplings of bird-scale ornithopters, enabling real-time predictive control. We validated the method with the XFly ornithopter flying along circular and three-dimensional racing trajectories and achieved a mean deviation from the reference trajectory between 6.5 and 9 cm at speeds up to 3 m/s, which represents an almost 10-fold improvement over prior ornithopter control methods.
Abstract (translated)
URL
https://arxiv.org/abs/2605.06042
PDF
-
InkDiffuser: High-Fidelity One-shot Chinese Calligraphy via Differentiable Morphological Optimization
2026-05-07 08:33:21Kunchong Shi, Jing ZhangAbstract
Current Chinese calligraphy generation methods suffer from poor stroke rendering and unrealistic ink morphology, resulting in outputs with limited visual fidelity and artistic fluidity. To address this problem, we propose \textbf{InkDiffuser}, a diffusion-based generative framework for one-shot Chinese calligraphy synthesis. To guarantee high-fidelity rendering, we introduce two core contributions: a high-frequency enhancement mechanism and a Differentiable Ink Structure (DIS) loss that explicitly regularizes ink morphology. Inspired by the observation that high-frequency information in individual samples typically carries contour details, we enhance content extraction by explicitly fusing high-frequency representations for more accurate font structure. Furthermore, we propose a differentiable ink structure loss that integrates differentiable morphological operations into the diffusion process. By allowing the model to learn an explicit decomposition of ink-trace structures, DIS facilitates fine-grained refinement of stroke contours and delivers significantly improved visual realism in the generated calligraphy. Extensive experiments on various calligraphic styles and complex characters demonstrate that InkDiffuser can generate superior calligraphy fonts with realistic ink rendering effects from only a single reference glyph and outperform existing few-shot font generation approaches in structural consistency, detail fidelity, and visual authenticity. The code is available at the following address: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.05865
PDF
-
EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function
2026-05-06 21:18:23Elias Stenhede, Joanna Sulkowska, Eivind Bj{\o}rkan Orstad, Henrik Schirmer, Arian RanjbarAbstract
We introduce EchoXFlow, a clinical echocardiography dataset for learning from ultrasound in its native acquisition geometry rather than from scan-converted Cartesian videos. Existing public datasets offer limited opportunities to study cross-modal relationships between cardiac anatomy, myocardial motion, and blood flow, as Doppler is typically absent or fused as RGB overlays, and acquisitions are released after lossy vendor display processing. EchoXFlow comprises 37125 recordings from 666 routine-care examinations, preserving the timing, geometry, and modality relationships needed for physically grounded echo learning. Each recording is retained as separable modality-specific streams: temporally resolved 1D, 2D, and 3D data alongside multiple Doppler modalities, paired with a synchronized ECG. Clinical annotations span guideline-based measurements to dense 2D myocardial contours and 3D left-ventricular endocardial meshes. With its associated open-source tooling, EchoXFlow enables cross-modal, acquisition-aware learning tasks that cannot be formulated from conventional scan-converted videos alone, and serves as a testbed for 4D vision and physically grounded multi-modal learning more broadly.
Abstract (translated)
URL
https://arxiv.org/abs/2605.05447
PDF
-
Uncertainty Estimation in Instance Segmentation of Affordances via Bayesian Visual Transformers
2026-05-05 10:40:16Lorenzo Mur-Labadia, Ruben Martinez-Cantina, Jose J. GuerreroAbstract
Visual affordances identify regions in an image with potential interactions, offering a novel paradigm for scene understanding. Recognizing affordances allows autonomous robots to act more naturally, could enhance human-robot interactions, enrich augmented reality systems, and benefit prosthetic vision devices. Accurate and localized prediction of affordance regions, rather than general saliency maps is crucial for these applications. We present a model for instance segmentation of affordances by adopting sample-based and ensembles approaches for uncertainty estimation. We extend an attention-based architecture for our novel task, showing with detailed ablation experiments the effects of each component. By comparing the distribution of these different detections, we extract pixel-wise epistemic and aleatoric variances at both the semantic and spatial levels. In addition, we propose a novel measure called Probability-based Mask Quality, which enables a comprehensive analysis of semantic and spatial variations in a probabilistic instance segmentation model. Our results show that the global consensus of multiple sub-networks of Bayesian models improve deterministic networks due to a better mask refinement and generalization. This fact, joined with the more powerful features extracted by attention-based mechanisms, represent an improvement of +7.4 p.p on the $F_{\beta}^w$ score in the challenging IIT-Aff dataset. Bayesian models are also better calibrated, producing less overconfident probabilities and with a better uncertainty estimation. Qualitative results show that aleatoric variance appears in the contour of the objects, while the epistemic variance is observed in visual challenging pixels, adding interpretability to the neural network.
Abstract (translated)
URL
https://arxiv.org/abs/2605.03614
PDF
-
Tracing Like a Clinician: Anatomy-Guided Spatial Priors for Cephalometric Landmark Detection
2026-05-05 04:33:45Sidhartha Mohapatra, Pallavi MohantyAbstract
When orthodontists trace cephalometric radiographs, they follow a structured workflow: identify the soft tissue profile, partition the skull into anatomical regions, trace contours, and locate landmarks using geometric definitions -- yet no automated system replicates this reasoning. We present a five-phase anatomy-guided initialization pipeline that translates this clinical workflow into computational operations, producing confidence-weighted spatial attention priors for a downstream HRNet-W32 detector. On 1,502 radiographs from three sources spanning 7+ imaging devices, the system achieves 1.04 mm mean radial error on 25 landmarks -- surpassing prior state-of-the-art (1.23 mm on 19 landmarks) by 15.4%, with twelve landmarks below 1 mm. A three-way controlled ablation reveals two striking findings. First, removing anatomical priors does not merely slow convergence -- it destroys generalization: both models converge to ~1.03 mm on validation, but diverge to 1.94 vs. 1.04 mm on the test set. Second, replacing anatomical priors with random-position Gaussians produces even worse generalization (2.24 mm), confirming that the improvement derives from anatomically correct positioning, not additional input channels. Clinical domain knowledge encoded as spatial priors provides an inductive bias that architecture and data augmentation alone do not provide.
Abstract (translated)
URL
https://arxiv.org/abs/2605.03358
PDF
-
Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations
2026-04-28 21:32:47Ujunwa Mgboh, Rafi Ibn Sultan, Joshua Kim, Kundan Thind, Dongxiao ZhuAbstract
Learning-based fluence map prediction offers a fast alternative to iterative inverse planning in intensity-modulated radiation therapy (IMRT), but its robustness under realistic distribution shifts remains unclear. We study a two-stage transformer pipeline that maps anatomy (CT and contours) to dose and then to beamlet fluence maps. We compare fluence-stage transformer backbones with hierarchical, global, and hybrid attention, trained with a physics-informed loss enforcing energy consistency. Robustness is evaluated under geometric perturbations, radiometric noise, reduced training data, and domain shifts using a prostate IMRT dataset, with additional evaluation of the dose stage on public datasets. Results show smooth degradation under moderate perturbations but sharp failures under severe rotations and noise. Hierarchical transformers (e.g., SwinUNETR) exhibit slower growth in upper-quartile energy error, indicating improved robustness. We further show that SSIM alone fails to capture clinically relevant errors, highlighting the need for physics-informed evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2605.00904
PDF
-
Trajectory Planning for an Articulated Commercial Vehicle using Model Predictive Contouring Control
2026-04-27 05:40:01A. J. Aertssen, R. G. M. Huisman, I. J. M. Besselink, J. Elfring, M. J. G. van de MolengraftAbstract
This paper presents a trajectory planning method for articulated commercial vehicles, specifically tractor-semitrailers, based on Model Predictive Contouring Control (MPCC). Although MPCC has proven effective for passenger cars, it is generally ill-suited for tractor-semitrailers. These vehicles are significantly larger, the semitrailer follows a different path than the tractor, and reversing maneuvers are unstable and prone to jackknifing. Furthermore, practical driving scenarios often require scenario-dependent prioritization of different vehicle `anchor points', e.g., prioritizing the semitrailer position during docking or the tractor position when parking to charge. Therefore, we extend MPCC to enable scenario-dependent weighting of these anchor points and incorporate explicit road-boundary constraints for the front and rear tractor axles and the semitrailer axle, thereby ensuring that all considered wheels remain within the drivable area. The simulation results demonstrate the successful navigation of a representative logistic scenario in both forward and reverse direction. Furthermore, the influence of the optimization parameters on the trajectories is analyzed, providing insights into controlling the vehicle behavior. Finally, first tests using a full-scale prototype vehicle show the practical applicability of the approach.
Abstract (translated)
URL
https://arxiv.org/abs/2604.24064
PDF
-
Knee-xRAI: An Explainable AI Framework for Automatic Kellgren-Lawrence Grading of Knee Osteoarthritis
2026-04-25 20:34:09Azmul A. Irfan, Nur Ahmad Khatim, Alfan Alfian Irfan, Achmad Zaki, Erike A. Suwarsono, Mansur M. AriefAbstract
Radiographic grading of knee osteoarthritis (KOA) with the Kellgren-Lawrence (KL) system is limited by inter-reader variability and the opacity of current deep learning approaches, which predict KL grades directly from images without decomposing structural features. We present Knee-xRAI, a modular framework that independently quantifies the three cardinal radiographic features of KOA (joint space narrowing [JSN], osteophytes, and subchondral sclerosis) and integrates them into an explainable KL grade classification. The pipeline combines U-Net++ segmentation for contour-based JSN measurement, an SE-ResNet-50 network for per-site osteophyte grading (OARSI scale), and a hybrid texture-CNN classifier for binary sclerosis quantification. The resulting 50-dimensional structured feature vector feeds two complementary classification paths. An XGBoost path supports SHAP-based feature attribution. A ConvNeXt hybrid path combines the structured vector with a full-image encoder for enhanced predictive performance. Evaluated on 8,260 radiographs from an OAI-derived dataset, the JSN module achieved a Dice coefficient of 0.8909 and an mJSW intraclass correlation of 0.8674 against manual annotations. The ConvNeXt hybrid path reached a test quadratic weighted kappa (QWK) of 0.8436 and AUC of 0.9017. The transparent XGBoost path achieved a test QWK of 0.6294 with full feature-level audit capability. Ablation confirmed JSN as the dominant predictor (QWK = 0.6103 alone), with osteophyte features providing consistent incremental gain (+0.0183) and sclerosis contributing marginally. Inference-time ablation of Path B confirmed the structured pathway contributes materially beyond the image encoder, with QWK drops of 0.098 (feature zeroing) and 0.284 (feature-image permutation). Knee-xRAI explicitly quantifies all three KL-defining radiographic features within a single auditable pipeline.
Abstract (translated)
URL
https://arxiv.org/abs/2604.23435
PDF
-
Come Together: Analyzing Popular Songs Through Statistical Embeddings
2026-04-24 18:00:48Matthew Esmaili Mallory, Mark Glickman, Jason BrownAbstract
Statistical modeling of popular music presents a unique challenge due to the complexity of song structures, which cannot be easily analyzed using conventional statistical tools. However, recent advances in data science have shown that converting non-standard data objects into real vector-valued embeddings enables meaningful statistical analysis. In this work, we demonstrate an approach based on logistic principal component analysis to construct embeddings from global song features, allowing for standard multivariate analysis. We apply this method to a corpus of Lennon and McCartney songs from 1962-1966, using embeddings derived from chords, melodic notes, chord and pitch transitions, and melodic contours. Our analysis explores how these song embeddings cluster by Beatles album, how songwriting styles evolved over time, and whether Lennon and McCartney's compositions exhibited convergence or divergence. This embedding-based approach offers a powerful framework for statistically examining musical structure and stylistic development in popular music.
Abstract (translated)
URL
https://arxiv.org/abs/2604.22925
PDF
-
Pre-process for segmentation task with nonlinear diffusion filters
2026-04-23 08:38:45Javier Sanguino, Carlos Platero, Olga VelascoAbstract
This paper deals with the case of using nonlinear diffusion filters to obtain piecewise constant images as a previous process for segmentation techniques. We first show an intrinsic formulation for the nonlinear diffusion equation to provide some design conditions on the diffusion filters. According to this theoretical framework, we propose a new family of diffusivities; they are obtained from nonlinear diffusion techniques and are related with backward diffusion. Their goal is to split the image in closed contours with a homogenized grey intensity inside and with no blurred edges. We also prove that our filters satisfy the well-posedness semi-discrete and full discrete scale-space requirements. This shows that by using semi-implicit schemes, a forward nonlinear diffusion equation is solved, instead of a backward nonlinear diffusion equation, connecting with an edge-preserving process. Under the conditions established for the diffusivity and using a stopping criterion for the diffusion time, we get piecewise constant images with a low computational effort. Finally, we test our filter with real images and we illustrate the effects of our diffusivity function as a method to get piecewise constant images. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.21422
PDF
-
PanGuide3D: Cohort-Robust Pancreas Tumor Segmentation via Probabilistic Pancreas Conditioning and a Transformer Bottleneck
2026-04-22 18:10:01Sunny Joy Ma, Xiang MaAbstract
Pancreatic tumor segmentation in contrast-enhanced computed tomography (CT) is clinically important yet technically challenging: lesions are often small, heterogeneous, and easily confused with surrounding soft tissue, and models that perform well on one cohort frequently degrade under cohort shift. Our goal is to improve cross-cohort generalization while keeping the model architecture simple, efficient, and practical for 3D CT segmentation. We introduce PanGuide3D, a cohort-robust architecture with a shared 3D encoder, a pancreas decoder that predicts a probabilistic pancreas map, and a tumor decoder that is explicitly conditioned on this pancreas probability at multiple scales via differentiable soft gating. To capture long-range context under distribution shift, we further add a lightweight Transformer bottleneck in the U-Net bottleneck representation. We evaluate cohort transfer by training on the PanTS (Pancreatic Tumor Segmentation) cohort and testing both in-cohort (PanTS) and out-of-cohort on MSD (Medical Segmentation Decathlon) Task07 Pancreas, using matched preprocessing and training protocols across strong baselines. We collect voxel-level segmentation metrics, patient-level tumor detection, subgroup analyses by tumor size and anatomical location, volume-conditioned performance analyses, and calibration measurements to assess reliability. Across the evaluated models, PanGuide3D achieves the best overall tumor performance and shows improved cross-cohort generalization, particularly for small tumors and challenging anatomical locations, while reducing anatomically implausible false positives. These findings support probabilistic anatomical conditioning as a practical strategy for improving cross-cohort robustness in an end-to-end model and suggest potential utility for contouring support, treatment planning, and multi-institutional studies.
Abstract (translated)
URL
https://arxiv.org/abs/2604.20981
PDF
-
Deep Supervised Contrastive Learning of Pitch Contours for Robust Pitch Accent Classification in Seoul Korean
2026-04-21 13:59:37Hyunjung Joo, GyeongTaek LeeAbstract
The intonational structure of Seoul Korean has been defined with discrete tonal categories within the Autosegmental-Metrical model of intonational phonology. However, it is challenging to map continuous $F_0$ contours to these invariant categories due to variable $F_0$ realizations in real-world speech. Our paper proposes Dual-Glob, a deep supervised contrastive learning framework to robustly classify fine-grained pitch accent patterns in Seoul Korean. Unlike conventional local predictive models, our approach captures holistic $F_0$ contour shapes by enforcing structural consistency between clean and augmented views in a shared latent space. To this aim, we introduce the first large-scale benchmark dataset, consisting of manually annotated 10,093 Accentual Phrases in Seoul Korean. Experimental results show that our Dual-Glob significantly outperforms strong baseline models with state-of-the-art accuracy (77.75%) and F1-score (51.54%). Therefore, our work supports AM-based intonational phonology using data-driven methodology, showing that deep contrastive learning effectively captures holistic structural features of continuous $F_0$ contours.
Abstract (translated)
URL
https://arxiv.org/abs/2604.19477
PDF
-
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
2026-04-21 11:17:09Shijie Wang, Zijian Wang, Yadan Luo, Haojie Li, Zi Huang, Mahsa BaktashmotlaghAbstract
Ultra-fine-grained visual categorization (Ultra-FGVC) aims to classify highly similar subcategories within fine-grained objects using limited training samples. However, holistic yet discriminative cues, such as leaf contours in extremely similar cultivars, remain under-explored in current studies, thereby limiting recognition performance. Though crucial, modeling holistic cues with complex morphological structures typically requires massive training samples, posing significant challenges in data-limited scenarios. To address this challenge, we propose a novel Divide-and-Conquer Holistic Cognition Network (DHCNet) that implements a divide-and-conquer strategy by decomposing holistic cues into spatially-associated subtle discrepancies and progressively establishing the holistic cognition process, significantly simplifying holistic cognition while reducing dependency on training data. Technically, DHCNet begins by progressively analyzing subtle discrepancies, transitioning from smaller local patches to larger ones using a self-shuffling operation on local regions. Simultaneously, it leverages the unaffected local regions to potentially guide the perception of the original topological structure among the shuffled patches, thereby aiding in the establishment of spatial associations for these discrepancies. Additionally, DHCNet incorporates the online refinement of these holistic cues discovered from local regions into the training process to iteratively improve their quality. As a result, DHCNet uses these holistic cues as supervisory signals to fine-tune the parameters of the recognition model, thus improving its sensitivity to holistic cues across the entire objects. Extensive evaluations demonstrate that DHCNet achieves remarkable performance on five widely-used Ultra-FGVC datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2604.19339
PDF
-
Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval
2026-04-21 06:32:34Hang Cheng, Fanhe Dong, Long ZengAbstract
This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-based 3D shape retrieval methods struggle in zero-shot settings due to the absence of category supervision and the extreme sparsity of sketch inputs. Our key insight is that large-scale pretrained diffusion models inherently exhibit open-vocabulary capability and strong shape bias, making them well suited for zero-shot visual retrieval. We leverage a frozen Stable Diffusion backbone to extract and aggregate discriminative representations from intermediate U-Net layers for both sketches and rendered 3D views. Diffusion models struggle with sketches due to their extreme abstraction and sparsity, compounded by a significant domain gap from natural images. To address this limitation without costly retraining, we introduce a multimodal feature-enhanced strategy that conditions the frozen diffusion backbone with complementary visual and textual cues from CLIP, explicitly enhancing the ability of semantic context capture and concentrating on sketch contours. Specifically, we inject global and local visual features derived from a pretrained CLIP visual encoder, and incorporate enriched textual guidance by combining learnable soft prompts with hard textual descriptions generated by BLIP. Furthermore, we employ the Circle-T loss to dynamically strengthen positive-pair attraction once negative samples are sufficiently separated, thereby adapting to sketch noise and enabling more effective sketch-3D alignment. Extensive experiments on two public benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in ZS-SBSR.
Abstract (translated)
URL
https://arxiv.org/abs/2604.19135
PDF
-
Sketch and Text Synergy: Fusing Structural Contours and Descriptive Attributes for Fine-Grained Image Retrieval
2026-04-17 06:20:56Siyuan Wang, Hanchen Gao, Guangming Zhu, Jiang Lu, Yiyue Ma, Tianci Wu, Jincai Huang, Liang ZhangAbstract
Fine-grained image retrieval via hand-drawn sketches or textual descriptions remains a critical challenge due to inherent modality gaps. While hand-drawn sketches capture complex structural contours, they lack color and texture, which text effectively provides despite omitting spatial contours. Motivated by the complementary nature of these modalities, we propose the Sketch and Text Based Image Retrieval (STBIR) framework. By synergizing the rich color and texture cues from text with the structural outlines provided by sketches, STBIR achieves superior fine-grained retrieval performance. First, a curriculum learning driven robustness enhancement module is proposed to enhance the model's robustness when handling queries of varying quality. Second, we introduce a category-knowledge-based feature space optimization module, thereby significantly boosting the model's representational power. Finally, we design a multi-stage cross-modal feature alignment mechanism to effectively mitigate the challenges of cross modal feature alignment. Furthermore, we curate the fine-grained STBIR benchmark dataset to rigorously validate the efficacy of our proposed framework and to provide data support as a reference for subsequent related research. Extensive experiments demonstrate that the proposed STBIR framework significantly outperforms state of the art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15735
PDF
