Object_Detection
-
Defake-o3: From Speculative Rationales to Verifiable Evidence for Explainable AIGI Detection
2026-08-17 08:30:32Bowen Deng, Jiahui Zhan, Yikun Ji, Haozhen Yan, Jianfu ZhangAbstract
The rapid progress of image generation models calls for AI-generated image (AIGI) detectors that are not only accurate but also explainable and reliable. While MLLM-based detectors can provide natural language explanations, existing methods often generate speculative rationales: they rely on vague or hallucinated artifacts, miss subtle localized flaws from the latest generators, and fail to provide evidence that can be visually verified. We present Defake-o3, an explainable AIGI detector that moves from speculative rationales to verifiable evidence. It combines interactive visual search with verifier-guided evidence alignment: the model iteratively zooms into suspicious regions to inspect fine-grained details, while an Evidence Verifier, trained from human verification annotations, provides reinforcement learning rewards that favor grounded evidence and penalize baseless claims. To support this objective, we construct GroundFake, a dataset designed for grounded explainable detection, with localized bounding-box evidence, human verification based on visual grounding and artifact specificity, corrected reasoning trajectories, and valid/invalid evidence supervision. We further introduce FakeFrontier, an out-of-distribution benchmark built from real images and outputs of 10 recent generators, together with an MLLM-based protocol for evaluating evidence quality and persuasiveness. Experiments on GroundFake, FakeFrontier, and additional out-of-distribution benchmarks show that Defake-o3 improves both detection accuracy and explanation quality, producing more localized, verifiable, and persuasive evidence.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16259
PDF
-
Beyond Clear Skies: Synthetic Seasonal and Weather Variations for Real-World Drone Detection
2026-08-17 07:14:45Tamara R. Lenhard, Andreas Weinmann, Tobias KochAbstract
Reliable drone detection under real-world deployment conditions requires training data that spans the full operational design domain, including adverse weather and seasonal appearance variation. However, acquiring and annotating such data at scale remains highly resource-intensive, as adverse-weather conditions are inherently difficult to control, reproduce, and sample systematically. Existing datasets therefore typically provide only limited coverage of such conditions. Conversely, synthetic data offers a scalable alternative: environmental variation becomes controllable, while modern game-engine-based pipelines provide realistic rendering and automatic annotations. Leveraging this potential, we introduce SynDroneVision-Weather (SDV-W), an systematic extension of SynDroneVision (SDV) targeting adverse-weather and seasonal domain shifts in urban drone detection. SDV-W comprises 55,187 annotated high-resolution images from three urban environments, rendered across three seasonal configurations and diverse weather conditions, including rain, snow, and fog at multiple severity levels. By preserving SDV's scene and trajectory configuration, SDV-W enables matched clean-adverse comparisons and quantification of condition-specific detector degradation. Across representative YOLO models and real-world datasets, we show that SDV-W improves detector reliability under adverse appearance shifts, reduces missed detections and false alarms, and is most effective as a complement to general-purpose synthetic drone-detection data. SDV-W will be publicly released upon paper acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16191
PDF
-
AIGC Video Detection based on the fusion of spatial-frequency-optical flow multimodal features
2026-08-17 05:38:08S. Hong, X. Q. Wang, C. Zhang, J. C. Wang, P. X. Duan, Y. W. WangAbstract
The rapid evolution of generative AI (e.g., Sora, Hunyuan) makes it essential to develop effective detection strategies that can generalize across ever-evolving synthesis techniques. This study is motivated by the observation of a fundamental challenge in generative models: the inherent difficulty of maintaining cross-modal consistency between appearance and motion. To this end, we propose a multi-modal framework for AIGC video forgery detection tasks, named Cross-Attention based Video Forgery Detector (CrossAtt-VFD), based on joint multi-view analysis of this http URL, we introduce a dual-branch architecture that simultaneously extracts spatial-frequency and optical-flow this http URL approach enables the modeling of videos from complementary perceptual this http URL core of this process is a dedicated cross-attention mechanism, which governs the alignment of the two modalities and translates cross-modal inconsistencies into a potent diagnostic signal. This multi-modal strategy facilitates the detection of motion that is statistically inconsistent with the visual appearance of a scene. Comprehensive experimental results demonstrated that our model achieves an accuracy of 94.22%, a precision of 91.67 %,and a recall of 96.25 %, effectively verifying the advantages of the multi-modal fusion strategy.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26274
PDF
-
Coverage Is Not Containment: A Fundamental Limit of Admission-Time Defenses Against Coordinated Poisoning of Vector Retrieval
2026-08-17 03:18:51Prashant Kumar Pathak, Tarun Kumar SharmaAbstract
Retrieval-augmented generation (RAG) answers a question by retrieving passages from a vector store and trusting them as context, so anyone who can add documents can try to steer the answer. A recent, appealing defense filters poisoning at ingestion, rejecting any document that behaves like a hub. We show it -- and every ingestion-time filter -- is defeated by a coordinated adversary that injects a handful of individually unremarkable documents which together surround one target query and seize its top-k (on BGE-large / BEIR, m=10 documents take 10/10; 9.9/10 on a live HNSW index). The attack is not theoretical. Realized as ordinary fluent text and run end-to-end through a BGE-large + HNSW + Qwen2.5-7B pipeline, it makes the generator emit the attacker's planted claim in 88% of targets, versus 0% without the injection. And no admission-time defense stops it: at ingestion an attack cone is geometrically identical to a legitimate niche upload, so -- measuring this directly -- the strongest trained classifier, given every feature and thousands of examples, separates the two no better than chance, catching 4.2% of attacks at a 1% false-positive rate. We prove this limit for the entire class of ingestion-time statistics (any decision from documents and reference queries alone), and it reproduces -- and worsens -- across two corpora and five encoders. The one signal that separates an attack from legitimate niche ingestion -- a query's demand -- is invisible before retrieval, which is also the escape: a retrieval-time detector that observes demand catches 100% of the attacks at the same 1% false-positive rate. Coverage of the query space by an admission gate is not containment of coordinated poisoning; robust defense must move past the front door, to demand.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16044
PDF
-
AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Driving
2026-08-17 02:52:01Yuting Wu, Dongfang Guo, Xiangzhong Luo, Qun Song, Rui TanAbstract
Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections. While adversarial training and input purification offer some protection, they often overfit to specific attack distributions and fail on adaptive adversaries. This paper presents AdROD, an embedded, stochastic ensemble defense software designed for autonomous driving. AdROD employs {\em low-rank HyperNetworks}, which require only 1.6\% of the parameter footprint of standard HyperNetworks, to generate diverse detectors at a per-frame rate, making it impractical for attackers to obtain the deployed detectors in time. To further improve adversarial robustness, AdROD incorporates a novel \emph{functional diversity} mechanism, which couples stochastic weight updates with unique input-space transformations. We design two serving modes of AdROD that strike different trade-offs between robustness and runtime overhead: AdROD-I, a continuous protection mode for maximum resilience that leverages inter-detector disagreement to recover compromised detections, and AdROD-II, an on-demand mode triggered by kinematic discontinuities in object tracking. Through comprehensive evaluation with synthetic benchmarks, physically deployed adversarial patches, and end-to-end safety tests in the OpenCDA co-simulator, AdROD outperforms five baseline defenses and exhibits superior generalizability compared with the evaluated adversarial-training baselines, while maintaining real-time performance for safely stopping the vehicle at a stop sign instrumented with adversarial patches.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16031
PDF
-
Tabletop Pen Manipulation With a Vision-Guided 4-DoF Arm
2026-08-16 23:51:05Anirudh Rangarajan, Bibit BianchiniAbstract
Low-cost four-degree-of-freedom (DoF) arms are among the most accessible robotic platforms. But they are, in theory, underactuated for picking up in situations where objects are at arbitrary orientations, a task that appears to require five degrees of freedom: the planar position (x and y), the height (z), a wrist rotation to align the gripper with the object, and gripper actuation, of which a four-DoF arm lacks the wrist rotation. This work shows that perception and motion planning can enable such an arm, a roughly $200 Waveshare RoArm-M2-S, under a fixed overhead camera to detect and color-sort writing utensils without that joint. A YOLO11n-OBB (You Only Look Once, oriented bounding box) detector locates each writing utensil; camera intrinsics and an ArUco reference pose convert its pixel coordinates to robot coordinates; and a color classifier labels it. The detected orientation angle determines the motion strategy: utensils close to the arm's fixed approach direction are picked up directly, and those at steeper angles are reoriented via corrective sweeps until they are graspable, after which they are picked up and sorted into the assigned color bin. Across 326 logged motions on seven writing utensils, the arm made 196 direct grasps and 130 corrective sweep passes, correcting misalignments up to 90 degrees, suggesting that clever task-informed engineering can compensate for a missing degree of freedom on tasks like this one.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15968
PDF
-
PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection
2026-08-16 15:27:50Chengyao Jia, Ruixuan WangAbstract
Out-of-distribution (OOD) detection remains challenging for image classifiers, especially when near-OOD samples lie close to in-distribution (ID) class boundaries. Recent vision-language detectors improve OOD detection through class semantics, local prompting, or LLM-generated outlier concepts, but seldom use language as explicit boundary evidence between confusing ID classes. We propose Pairwise Witness Local Rejection (PWLR), which uses an MLLM offline to describe visible local cues that favor one ID class over a specific rival class. These cue phrases are then screened with ID-only data under a frozen vision-language backbone, so that only reliable local verifiers are kept. At inference, PWLR first retains a small set of globally plausible classes, then checks whether any of them is locally supported against its most relevant rivals, and finally combines this pairwise local evidence with the global class score through calibration. Experiments on ImageNet-100 far-OOD, cleaner/challenging OOD and near-OOD benchmarks show that PWLR consistently improves strong vision-language baselines across multiple backbones. Source code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15802
PDF
-
KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving
2026-08-16 15:23:25Minsoo Cheong, Woosang Lim, Vincent-Daniel Yun, Sungjoo YooAbstract
KV-cache eviction caps the memory cost of long reasoning traces but is inherently lossy because the model decodes from a partial view of its history. Under aggressive budgets, this not only lowers accuracy but can also cause runaway degeneration, where the model produces incoherent or repetitive tokens until reaching the length limit. We characterize much of this loss as an information gapf caused by missing context, rather than a capability gap caused by limited model capacity. An evicted 7B model and a full-context 1.5B model make complementary errors, and an oracle choice between their answers recovers 79% of the accuracy gap to the full-KV 7B model. Based on this observation, we propose KV-Rescue, a training-free inference framework that bridges the information gap introduced by KV eviction using a lightweight full-context helper. KV-Rescue interleaves reasoning steps from the two models into a shared trajectory. An online detector uses entropy and compressibility to terminate the generation of incoherent or repetitive base-model candidates early. Across five math benchmarks with Qwen2.5-Math 7B and 72B, KV-Rescue recovers an average of 87% of the accuracy lost to eviction at eviction budget B=64. A decode-cost analysis further shows that preventing runaway degeneration cuts base-model token generation by 43% on average.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15797
PDF
-
TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity
2026-08-16 14:40:44Armin SteinhauserAbstract
We introduce TinyCast, an attention-free zero-shot forecaster that emits a predictive distribution from 146,505 parameters, on the premise that at this size the periodic structure of a context is worth computing rather than learning. A zero-parameter spectral detector supplies the dominant periods, the context is folded on their phase, and a dilated convolutional encoder and a block-autoregressive quantile decoder model the rest. It is smaller than every zero-shot entry on the GIFT-Eval board whose parameter count can be established. On probabilistic accuracy it defines the size-accuracy frontier. Among zero-shot entries declaring no test-data leakage it is the only one below 1.4M parameters that emits a predictive distribution, and every entry scoring better carries at least that budget. On Chronos-ZS and fev-bench every neural model ahead of it carries at least 28 times its parameters. Because the mixing path is convolutions and matrix multiplications only, it exports to static INT8 and forecasts end to end on an embedded device without per-signal fitting.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15767
PDF
-
YOLO26-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling
2026-08-16 12:36:12Sompote Youwai, Pawarotorn Chaipetch, Hathairat Samaikul, Theerayut YonsengAbstract
Automated pavement-distress detection is commonly framed as a small-object problem, motivating high-resolution P2/4 detection heads and lossless downsampling. We present YOLO26-RD, an end-to-end (NMS-free) detector built on YOLO26 with two lightweight novel modules (LearnableContrast, a 494-parameter differentiable analogue of CLAHE that adapts contrast per tile inside the network, and EdgeSPD, a Sobel-gated space-to-depth downsampler adding only 2 parameters over SPD-Conv), and we subject the design to a data-first audit on a 7,618-image road-survey dataset (alligator crack, linear crack, patching). The audit falsifies the small-object premise: 92% of instances are COCO-large, and linear cracks are extreme-aspect structures (median 10:1) whose difficulty is sensitivity, not localization. Guided by this analysis, we remove the P2 detection level while retaining P2 features in the fusion path, which improves mAP50 by 2.8 points over the full YOLO26-RD model and reduces epoch time by 8%. Trained from scratch at 640x640, our best screening configuration reaches 0.787 mAP50 on the validation split versus a 0.771 project baseline (a stock YOLO26-s of uncontrolled recipe), with the largest per-class gain on the rarest class (patching, 2.6 points over baseline; 9.4 over the unmodified YOLO26-RD control under an identical recipe). A failure-mode decomposition further attributes the residual error of the bottleneck class (crack, approximately 0.74 across all architectures tested) to train/validation distribution shift on crack orientation and length, sub-pixel crack width at 640x640, and label incompleteness, factors no architecture change can address. We argue that for pavement imagery, measurement-driven subtraction outperforms module accretion, and we release our audit protocol alongside the model.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15713
PDF
-
Training-Free Long-Term Multi-Object Tracking for Sports Video Analytics
2026-08-16 11:33:00Tomasz Stanczyk, Seongro Yoon, Francois BremondAbstract
Long-term multi-object tracking in sports remains challenging due to frequent occlusions, rapid camera motion, and repeated player reappearances. We introduce McByte++, a training-free tracking-by-detection framework that integrates lightweight mask propagation, conditional camera motion compensation, and online re-identification within a unified pipeline. Compared to its predecessor, McByte++ substantially improves runtime efficiency while enhancing identity preservation. On SoccerNet-tracking and SportsMOT benchmarks, McByte++ achieves up to +3.0 HOTA and +6.1 IDF1 improvements over the original McByte in the online setting, with further gains when combined with offline global association. Replacing heavy segmentation components and optimizing motion modeling yields up to an order-of-magnitude speed increase. All results are obtained without detector retraining or dataset-specific tuning. Code will be made available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15688
PDF
-
Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors
2026-08-16 06:10:40Iyad Assaad Nekka, Hamida Seba, Walid Khaled Hidouci, Karima AmroucheAbstract
Anomaly detection in dynamic graphs underpins financial fraud analysis, intrusion detection, and platform integrity, where automated decisions require human-interpretable justifications. StrGNN, the strongest performer in recent benchmarks, produces no explanation: when an edge is flagged, the analyst receives only a score. Explanation metrics are undefined for StrGNN because no attribution vector exists. This paper closes that gap. We present X-StrGNN, a post-hoc explanation layer that wraps a trained, frozen StrGNN and emits, for every flagged edge, dual attributions: a structural attribution identifying which contextual interactions in the enclosing subgraph drove the decision, and a temporal attribution identifying which historical snapshot carried the signal. Both attributions are multiplicative masks identically one in the unexplained pass, so the layer is an exact pass-through: detection is preserved to machine precision, verified rather than asserted (Delta AUC = 0.0000, Delta AP = 0.0000, Delta P@100 = 0.0000). Attribution costs 0.66 ms per edge, making explanation of an entire alarm list feasible. We conduct the first controlled design study of attribution strategies for this architecture, comparing gradient attribution, per-instance mask optimisation, and amortised parameterisation under one protocol, one budget, and three seeds. X-StrGNN attains the highest stability (0.913) at 268x lower cost than per-instance optimisation, and its temporal attribution (1.601 against a measured random floor of 0.973) is separably better than its ablated control, while per-instance optimisation - the most expensive strategy - falls below that floor. Code, protocol, and per-seed measurements are released.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15559
PDF
-
Degenerate in Whose Frame? An Equivariance Condition for Degeneracy Detection in LiDAR Registration
2026-08-16 05:04:11Yujie Zhang, Chunlei Zhao, Yuzong Lin, Yuxuan Guo, Xiaohui Jia, Jinyue LiuAbstract
Degeneracy detectors for LiDAR registration commonly return six per-axis binary labels. We ask whether these labels are properties of the scene. Under a body-frame change, the point-to-plane information matrix transforms by congruence, H' = Ad(T)^T H Ad(T), not similarity. Congruence preserves nullity and, through the adjoint reparameterization, identifies the same physical twist subspace; the per-axis footprint and a thresholded spectrum need not be invariant. In a noise-free circular tunnel, shifting the origin by one metre changes which degrees of freedom are flagged. A generalized criterion Hv = lambda Mv is universally frame-independent over positive-semidefinite information forms if and only if its metric rule is equivariant. No fixed metric qualifies, while a rig-adapted one exists only at zero screw pitch, met in one of nineteen surveyed calibrations. The equivariant point-displacement metric M = sum_i J_i^T J_i yields dimensionless, scene-scale-invariant generalized eigenvalues. They are invariant to body frame, consistent changes of length unit and scene scales; the threshold also transfers empirically across sequences. Across 365 frame pairs from four public sequences, labels rarely change at practical extrinsic magnitudes, yet a remapping estimator's correction differs between body-frame choices on 44.5-69.5% of pairs, with a median of 0.7-4.0 mm and a maximum of 0.87 m. The per-axis footprint changes even under the equivariant metric, placing the fundamental issue in the reported quantity.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15532
PDF
-
MM-BEV: Enhancing Timeliness by Computing Where and When it Matters
2026-08-15 22:42:47Liangkai Liu, Kang G. ShinAbstract
Multimodal bird's-eye-view (BEV) perception combines LiDAR depth accuracy with dense camera semantics, but its high computational cost and imperfect sensing conditions make real-time deployment challenging. Existing methods largely compress individual detectors and overlook three opportunities: structured sparsity within camera and LiDAR inputs, timing misalignment between modalities, and the fact that many detected objects do not affect the planner's immediate action. We present MM-BEV, a real-time multimodal BEV system guided by a simple principle: compute where and when it matters. MM-BEV divides perception into mandatory work for safety-critical objects within braking distance of the ego vehicle and with short time-to-collision (TTC), and optional work for less urgent regions. It prioritizes mandatory work and reduces or sheds optional work under tight compute budgets. MM-BEV integrates four mechanisms: (1) a criticality-ranked temporal ROI selector based on motion-extrapolated detections from prior frames; (2) sparse, ROI-aware feature extraction using shared-shape camera crops at context-adaptive resolution and ROI-aware LiDAR voxelization; (3) a latency-aware coordinator that adapts LiDAR sweeps, image resolution, and keyframes according to scene dynamics and TTC; and (4) an asynchronous scheduler that decouples sensing from inference and skips stale frames. On nuScenes, MM-BEV reduces inference latency by 1.96x and end-to-end latency by 2.93x, with no loss in geometry-critical recall and only a 0.2 percentage-point drop in safety-critical recall. On a Clearpath Husky A300 equipped with an Ouster-128 LiDAR, BEV cameras, and a Jetson AGX Orin, MM-BEV further reduces mean latency by 2.11x, demonstrating its potential for real-world autonomous systems.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15437
PDF
-
Boundary-Aligned Contribution Routing for Robust Optical--SAR Object Detection
2026-08-15 14:37:23Haifa Zhang, Yijing Wang, Haoyu Wang, Zheng Li, Zhiqiang ZuoAbstract
Optical imagery provides rich appearance cues, whereas synthetic aperture radar (SAR) offers observations that are less sensitive to illumination and weather, making optical--SAR fusion attractive for remote-sensing object detection. However, the presence of multiple modalities does not guarantee beneficial fusion: imperfect spatial, temporal, and semantic correspondence can make an otherwise intact stream conditionally harmful and induce negative cross-modal transfer. We handle this issue through a model-specific task-utility perspective and learn task-conditioned contribution routing using detection supervision alone. The proposed fusion-boundary-aligned routing regulates each modality's contribution before the first learned cross-modal feature-value mixing operation. For architectures with frequent shallow interaction, a Feature Router performs cross-conditioned, group-addressable modulation near the input; for dual-backbone architectures, a Dual-Statistic Semantic Router predicts stream-level contribution weights from modality-specific average and maximum statistics before late semantic fusion. The routers require no explicit utility supervision, quality labels, reconstruction, or distillation. Experiments on M4-SAR and SpaceNet6-OTD cover nominal full inputs, controlled correspondence shifts, missing modalities, and four nonzero modality-corruption scenarios. Across the reported clean-training controls, routing improves full-input $\text{mAP}_{50}$ by 0.5--5.9 points. Relative to the corresponding modality-dropout baselines, it raises missing-modality $\text{mAP}_{50}$ by 7.6--41.6 points and reduces the negative-transfer rate by up to 12.7 percentage points. Spearman correlations between the learned routing weights and model-specific leave-one-modality-out utility range from 0.45 to 0.66, supporting the task-utility interpretation of the routing coefficients.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15261
PDF
-
Robust structure from motion for aerial-ground images via detector-free feature matching and multi-view track refinement
2026-08-15 14:16:02San Jiang, Hui Wang, Xing Zhang, Zhongwen Hu, Zhijun Wang, Ruisheng Wang, Wanshou Jiang, Qingquan LiAbstract
Integrated 3D reconstruction from aerial-ground images is essential for generating high-precision urban 3D models, yet severe variations in viewpoint, scale, and rotation make robust feature matching highly challenging. To address these limitations, this study introduces a rotation-robust detector-free matching network coupled with multi-view track refinement for incremental Structure from Motion (ISfM). The proposed workflow features four key modules. First, rotation-aware feature extraction replaces traditional convolutions with an Omnidirectional State Space Block (OSS Block) that selectively scans across eight symmetrical directions to model long-range spatial dependencies and synthesize rotation-invariant feature maps. Second, multi-scale attention transformation utilizes quadtree attention to build a hierarchical token pyramid that isolates high-association token regions and discards irrelevant areas, capturing long-range context with linear computational complexity. Third, bi-directional feature matching executes a symmetric coarse-to-fine matching scheme where coarse alignment computes dual-direction Softmax confidence matrices under mutual nearest neighbor constraints, and fine alignment uses a multi-layer perceptron to regress sub-pixel coordinate offsets. Finally, multi-view track refinement employs an integrated indexing structure to evaluate localized spatial proximity and link disjoint sub-tracks to the highest-confidence anchor point, ensuring stable feature repeatability across the ISfM pipeline. By using real aerial-ground datasets, experimental results demonstrate that the proposed method improves AUC at 5° pose error by 93.9% compared with LoFTR and achieves the highest precision in ISfM reconstruction, with the improved accuracy ranging from 27.6% to 32.7%. The proposed method provides a reliable solution for integrated 3D reconstruction of aerial-ground images.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15251
PDF
-
UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models
2026-08-15 13:53:59Lei Tan, Shuwei Li, Mohan Kankanhalli, Robby T. TanAbstract
Vision-Language Large Models (VLLMs) are promising for AI-generated image (AIGI) detection because they can produce both a prediction and a natural-language output. However, most existing VLLM-based detectors primarily fine-tune the language side while giving limited attention to low-level visual forensic cues. They also often depend on manually crafted prompts or human-annotated rationales, which limits this http URL present UC-VLM, a unified multi-stage framework for AIGI detection that relies solely on binary supervision. UC-VLM first identifies effective instruction variants automatically. It then reuses the same binary label within a multi-stage training framework: (i) a visual discrimination objective that strengthens sensitivity to non-semantic forensic cues, and (ii) a label-conditioned generation objective that uses the binary label to supervise textual outputs. This design turns weak binary supervision into a shared supervision signal for both the visual pathway and the language output. Our key novelty is a unified multi-stage binary-supervised framework that consistently reuses the same authenticity labels for visual adaptation and label-conditioned text generation, while leveraging automatically optimized instructions to reduce prompt sensitivity without requiring human-written rationales or hand-crafted this http URL show that UC-VLM achieves 96.1% average accuracy on GenImage, exceeding the strongest prior result by 4.6%, and obtains 69.6% / 77.9% accuracy on Chameleon under ProGAN / SDV1.4 training, surpassing the best baseline by 11.2% / 15.3%, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15238
PDF
-
SPEANet: Structural Prior Enhanced Attention Network for Parameter-Efficient Remote Sensing Object Detection
2026-08-15 07:54:56Wei Lu, Junjie Li, Feifei Sang, Si-Bao ChenAbstract
Remote sensing object detection (RSOD) requires compact backbones capable of preserving weak geometric cues under extreme scale variation and background clutter. Fixed structural operators provide complementary contour and frequency responses without introducing learnable operator coefficients. However, directly injecting these responses can amplify content-irrelevant textures, while applying a uniform operator design across the hierarchy may be poorly matched to stage-specific representation requirements. We propose the Structural Prior Enhanced Attention Network (SPEANet), a parameter-efficient RSOD backbone that integrates fixed operators through stage-specific prior extraction and context-conditioned response modulation. SPEANet assigns smoothed contour and multi-order directional modeling to shallow, high-resolution features, while employing a compact approximation-detail interaction mechanism in deeper stages. Learned spatial gates regulate the resulting prior responses before residual fusion. Experiments on five benchmarks, together with evaluations across seven detection frameworks on DOTA-v1.0, achieve a favorable accuracy-parameter trade-off. With Oriented R-CNN, SPEANet achieves 78.55\% mAP on DOTA-v1.0, 72.24\% mAP on DOTA-v1.5, and 67.30\% mAP on DIOR-R using 23.0M total parameters, including a 5.97M-parameter backbone.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26064
PDF
-
Distribution-free false-alarm calibration and chance-corrected spatial evaluation for industrial anomaly detection
Abstract
Studies of industrial visual inspection commonly report the area under the receiver operating characteristic curve (AUROC) and the overlap between anomaly maps and defect masks. Neither measure specifies the false-alarm rate at a selected threshold, while recurrent defect locations and mask geometry can inflate overlap. We combine a distribution-free upper tolerance threshold with a paired-minus-crossed spatial test. This test compares each detector's score-contributing locations with the matched defect mask and with masks from other images; the difference in rates defines spatial-evidence lift relative to the empirical chance-overlap rate. We evaluate three detectors on 120 point-defect images from three ISP-AD modalities and three fixed data splits. Of 378 alarms, 230 overlap the matched mask. Paired and crossed rates are nevertheless similar in eight of nine detector--modality cells; only DINOv2--ASM has a positive 95\% bootstrap lower bound (lift 0.259, 95\% interval 0.159--0.347). On the independent Magnetic Tile Defect dataset, the same analysis gives lifts of 0.203 (0.169--0.236) for Wide ResNet-50 (WRN50) patch memory and 0.231 (0.202--0.262) for Vision Transformer B/16 (ViT-B/16) patch memory, with one-sided permutation $p=10^{-5}$ for both. When crossed masks are restricted to the same defect class, the lifts remain 0.185 and 0.210. Exact sample planning shows that, with 150 calibration normals, a 95\%-confidence distribution-free claim is supported only for target false-positive rates of 1.98\% or higher; a 1\% target requires at least 299 normals. The results support reporting operating-point performance and chance-corrected spatial evidence alongside AUROC and raw mask overlap.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15090
PDF
-
Risk-Adaptive Edge--Cloud Visual Reasoning for Communication-Efficient Autonomous Driving
2026-08-15 02:36:01Meng Ma, Shuyang Li, Naigang Wang, Ruimin KeAbstract
Cloud-hosted vision-language models (VLMs) offer greater contextual reasoning capabilities than smaller onboard models, but frequent visual uploads increase communication overhead and add network and inference latency to tactical decisions. We present a risk-adaptive edge-cloud architecture in which onboard traffic assessment determines when cloud reasoning is requested. An onboard VLM and a lightweight detector capture temporal traffic conditions and path-relative hazards for conservative local response and selective cloud access. The cloud model provides tactical advice, while validation, vehicle control, and automatic emergency braking remain local. In CARLA experiments, our method matched the task success rate of periodic cloud access while reducing cloud requests by 54.1% and recording fewer automatic emergency braking (AEB) activations. In a delayed-roadwork ablation, semantic events triggered requests before the next scheduled audit. Across three emulated network profiles, the method continued to reduce cloud traffic, although lane changes took longer than with periodic access. Onboard traffic assessment therefore served as a practical trigger for selective VLM inference in these experiments.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14991
PDF
