paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

New Orthogonal Multiwavelet Filters Derived by Matrix Spectral Factorization

Vasil Kolev, Todor Cooklev, Fritz Keinert

The paper considers the construction of two new orthogonal multiwavelets with supercompact support by using the Fast Bauer's method for matrix spectral factorization on the matrix product filter of the orthogonal CL multiwavelet filter. The new multiwavelets possess orthogonality, symmetry/antisymmetry, and one of them provides better coding and smoothness than other supercompact multiwavelets. The performance of the new multiwavelet filters in subband-based edge detection, grayscale and color image compression and 1D and 2D signal denoising is compared with the GHM, SA4, CL, Integer Haar and Alpert multifilters. The comparative analysis shows that new multiwavelets can provides better human visual measures, SSIM and MS-SSIM in image compression and denoising applications.

arXiv

CausalSplat: Towards Comprehensive Hierarchical Reasoning in 3D Gaussian Splatting

Jiayu Ding, Meilu Song, Yun Chen, Wei Gao, Ge Li

While 3D Gaussian Splatting (3DGS) has advanced open vocabulary scene understanding, existing methods remain confined to explicit queries. They struggle to interpret implicit intents, complex spatial constraints, and commonsense reasoning required for practical embodied interactions. To address this gap, we introduce the task of reasoning 3D Gaussian segmentation and construct two benchmarks, Causal-LERF and Causal-ScanNet. These benchmarks systematically evaluate commonsense, spatial, affordance, and counterfactual reasoning. Evaluations reveal that current state of the art methods perform poorly on these reasoning challenges. Therefore, we propose CausalSplat, a framework that integrates vision-language models with 3D scene graphs to disentangle explicit structural perception from implicit logical inference. Extensive experiments demonstrate that CausalSplat achieves state of the art performance on our reasoning benchmarks while showing strong generalizability on standard referring and open vocabulary 3D segmentation tasks. Project Page: https://jiayuding031020.github.io/CausalSplat

arXiv

Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization

Swarnim Maheshwari, Syed Imam Ali, Vineeth N Balasubramanian

Most image colorization systems operate in $Lab$ space by predicting chroma ($ab$) while preserving an input-derived luminance channel ($L$). While effective on standard benchmarks, this fixed-luminance design restricts brightness changes and becomes unreliable when grayscale formation deviates from natural-image luminance, as in historical orthochromatic photography. We propose a luminance-agnostic colorization framework that formulates colorization as full-RGB image editing using a foundation image-editing model. To bridge modern panchromatic and historical orthochromatic conditions, we introduce a mixed grayscale objective that trains the model under both standard luminance grayscale and a red-insensitive grayscale formation. Experiments on COCO, ImageNet, and a multi-instance benchmark show that our method is competitive on standard grayscale inputs and substantially more robust under orthochromatic inputs, with qualitative comparisons and a human study indicating fewer visible color artifacts.

arXiv

Bridging Event Streams and DiT: Event-Guided Video Frame Interpolation

Guixu Lin, Yuyang Yu, Xiang Ji, Linyao Chen, Zhengwei Yin, Mengshun Hu, Mingdeng Cao, Shengfeng He, Yinqiang Zheng

Latent diffusion models have recently advanced video frame interpolation by synthesizing intermediate frames between input images. However, handling large temporal gaps and complex motion remains challenging, often resulting in motion blur, structural distortions, and temporal inconsistencies. Event cameras provide high-temporal-resolution motion cues that are well suited for bridging these gaps and improving interpolation quality. To exploit this advantage without training an event-assisted model from scratch, we propose an adapter-based framework that incorporates event-derived cues into a pre-trained image-to-video diffusion model with minimal architectural changes. Specifically, our method leverages Image Warped Events (IWEs) and bidirectional sparse optical flow to provide spatially and temporally aligned guidance during generation. By injecting these event-guided structural and motion cues into the diffusion process, our approach reduces interpolation artifacts and improves both reconstruction fidelity and temporal coherence. Experimental results on real and synthetic benchmarks show that our method consistently outperforms existing state-of-the-art approaches. The project page is at https://joseph-lin-tech.github.io/BridgeEventDiT-VFI/.

arXiv

Algorithmic statistics of retinal images

Loan Huynh, Ronald Zambrano, Layton Aho, Fabio Lavinsky, Gadi Wollstein, Joel S. Schuman, Andrew R. Cohen

There has been a tremendous amount of image processing and machine learning research to measure and classify disease progression from live optical coherence tomography (OCT) imaging of the retina. The images considered here are large, complex, three-dimensional (3-D) and difficult to visualize effectively. Many current supervised machine learning approaches, \emph{e.g.} neural networks, are non-metric meaning that any features or measurements generated can introduce systematic distortion that may be correlated with underlying non-meaningful physiological differences. Here we present a metric learning approach using the normalized compression distance (NCD) combined with anisotropic structure-enhancing filters to quantify and visualize the principal differences among a collection of 3-D retinal images. We validate the NCD-measured structural differences between pairs of images against the physician-measured change in visual field function, achieving a prediction error of $\sim$ 0.5 dB, more accurate than non-metric deep learning approaches. The normalized compression vectors (NCV) are proposed as a feature set measuring visual differences among a collection of 3-D microscopy images. The utility of the NCV for visualizing and measuring patterns of change is demonstrated for a human with moderate non-progressing glaucoma and for a non-human primate model using intraocular pressure setting manipulation. We conclude with a brief simulation of non-metric embedding features, \emph{e.g.} from neural networks, introducing class-correlated statistical distortion.

arXiv

VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction

Hongjin Ji, Guoyang Xia, Luoyang Sun, Fangxiang Feng, Lei Ren

Test-time training (TTT) offers a lightweight way to adapt vision--language--action (VLA) policies from unlabeled deployment streams, but it remains difficult to use reliably in closed-loop manipulation. A shared adaptation space can mix incompatible task corrections, while an online update can alter subsequent actions before its consequences are known. We introduce a reliable TTT framework for VLA policies (VANE). VANE conditions prompt adaptation on the current vision--language context and learns from the future visual consequences of executed actions. Candidate updates are isolated from the live policy, evaluated on subsequent observations, and committed only when supported by future evidence, making adaptation selective and reversible. On SimplerEnv WidowX, VANE improves average success by $3.2$ percentage points over the corresponding TTT baseline. Results on Google Robot further show that deployment-time gains remain task- and embodiment-dependent. Together, these results demonstrate a constrained, evidence-based approach to adapting VLA policies during interaction.

arXiv

Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction

Jingxian Xu, Yuhao Huang, Rusi Chen, Yanfeng Zhou, Dong Ni

Accurate landmark localization in medical images is a fundamental step for quantitative clinical measurement and downstream analysis. Existing localization methods have advanced, among which multi-stage refinement is a superior solution. Although this strategy mitigates the anatomical ambiguity inherent in single-stage global predictions, its high computational cost limits practical applicability. In this work, we propose a parameter-economic model, PPOC-LL, which leverages Prototype learning-based Progressive Offset Correction for Landmark Localization. Our contribution is three-fold. First, to drive coarse-to-fine landmark optimization, we introduce a multi-scale dynamic perception strategy for patch-level feature pyramid modeling. Second, to effectively handle anatomically similar patterns, we design a similarity-driven prototype learning mechanism that captures informative local semantics for robust offset prediction. Last, to stabilize the model learning and improve the overall performance, we incorporate a novel error-aware reliability regularization via tolerance-based balancing. We collected a large validation cohort, including two public and one private datasets spanning X-ray and ultrasound modalities, covering cephalometric, symphysis-fetal head, and fetal heart landmarks. Extensive experiments demonstrate that PPOC-LL achieves satisfactory performance with a favorable trade-off between accuracy and model complexity.

arXiv

Ego-OSCAR: Egocentric Open source Stereo CAptuRe System

Gunjan Paul, Senthil Palanisamy, Satpal Singh Rathore, Pratyush Kumar Patnaik, Shubhanshu Khatana, Abhishek Anand

We present Ego-OSCAR, an open-hardware, low-cost, head-mounted stereo-inertial capture device for egocentric data collection in the wild. EgoOSCAR pairs a hardware-synchronized global-shutter stereo camera with a 6- axis IMU, an embedded Linux SBC for on-device video encoding, and a realtime microcontroller for user feedback and watchdog functions. The complete bill of materials is under USD 200 per unit, using only commercially available components and 3D-printed parts. Alongside the device, we release a complete software stack (hardware-accelerated recording pipeline, IMU sampling daemon, time-synchronization tooling, and watchdog firmware) and roughly 550 hours of egocentric stereo video per camera with synchronized IMU, collected by a distributed contributor network across everyday indoor environments. The release is annotated rather than raw: free-form action captions cover essentially the entire recorded timeline with an open vocabulary, and per-frame 3D hand reconstructions ship alongside per-session stereo calibration. Ego-OSCAR does not aim to match the per-unit fidelity of research-grade systems such as Project Aria; it aims to be the cheapest defensible substrate for crowdsourced egocentric capture, and to lower the activation energy for any team that wants to collect egocentric data at scale. All hardware designs, software, and the dataset are open-sourced

arXiv

LoDA: A Level of Detection Aware Method and a Multimodal Sensing Benchmark for Object Level Change Detection

Haitian Wang, Xinyu Wang, Sheldon Fung, Xian Zhang, Zichen Geng

High-definition 3D LiDAR maps are important for autonomous driving and smart-city services, which require reliable detection of object-level changes in multi-temporal urban LiDAR to keep digital maps aligned with the physical world. Existing approaches from raster height differencing to depth image and point-cloud networks often remain tile-based and threshold-driven, yielding per-point scores without explicit detection limits or consistent object-level labels. We propose an object-level 3D change-detection pipeline that integrates detection-limit-aware registration, geometry-driven object proxies with rule-based semantic and instance segmentation, and displacement cues in height, volume, and surface-normal direction to assign five change labels with confidence. By decoupling registration, geometry, and semantics, the pipeline propagates pose uncertainty into spatially varying detection limits, stabilizes cross-epoch correspondences, and suppresses false changes caused by residual misalignment and density variation. We also present LoDA, a level-of-detection (LoD) aware benchmark for the Subiaco district with fused multi-temporal vehicle-LiDAR maps constructed with LiDAR, GNSS, and IMU support, semantic instances, and object-level annotations. On this benchmark, our method achieves 95.0% accuracy, 90.8% macro F1, and 83.0% macro IoU, exceeding the best baseline by 8.7 IoU points and 4.4 F1 points. On the public Urb3DCD-V2 benchmark evaluated under the official point-wise protocol, it reaches 96.81% mean accuracy and 89.52% mean change IoU, improving over the strongest reported baselines by 1.36 points in mAcc and 3.18 points in mIoUch.

arXiv

Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving

Meibo Hu, Jiamian Wang, Pichao WANG, Zhiqiang Tao

Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs and high-level navigation instructions directly to executable trajectories. However, in practice, these models exhibit a persistent command-following gap: predicted trajectories often show weak sensitivity to navigation commands, resulting in incorrect behavior at critical decision points. We identify this issue as a form of conditional policy collapse, where regression-based training under multimodal trajectory distributions encourages the model to rely on dominant visual priors while marginalizing the language-conditioned signal. To address this issue, we introduce a principled formulation of classifier-free guidance (CFG) for regression-based vision-language driving. We show that CFG can be interpreted as isolating the instruction-induced residual in the action space by contrasting conditional and unconditional predictions, thereby explicitly amplifying the effect of the navigation command at inference time. However, a standard two-pass CFG introduces prohibitive latency for real-time control and produces noisy instance-level guidance directions. Building on a mean-shift interpretation of CFG, we propose Latent-Centroid Steering (LCS), a single-pass guidance mechanism that replaces instance-level residuals with class-level latent shifts. By projecting conditional representations toward precomputed command-specific centroids, LCS performs class-level latent steering based on cluster geometry that is both more stable and computationally efficient. We demonstrate that LCS reduces inference latency by approximately 50% while achieving stronger command adherence and improved driving performance on both closed-loop (Bench2Drive) and open-loop (nuScenes) benchmarks. Code will be released.

arXiv

Meshy T2: Fast Native Mesh Generation with Flow Matching

Jiale Xu, Rendong Liang, Yuhao Long, Siyuan Shen, Zangyueyang Xian, Xiaofei Wu, Zeyi Xu, Yuanming Hu

Polygonal meshes are the standard surface representation of modern 3D pipelines, and generating high-quality meshes with artist-style topology is essential for film, gaming, and interactive 3D applications. Mainstream approaches serialize a mesh into a token sequence and decode it autoregressively, which is slow at inference and sensitive to error accumulation, making them impractical for interactive asset creation. We present Meshy T2, a fast native mesh generation framework built on flow matching. At its core is a vertex-set mesh VAE that encodes a mesh into one continuous latent token per vertex and decodes vertices, edge connectivity, and face winding order in a single pass, preserving high-precision geometry and artist-authored topology without vertex quantization or welding. Generation proceeds as a coarse-to-fine cascade of two flow-matching models: an image-conditioned voxel flow first sketches the overall shape as a coarse occupancy scaffold, and a mesh flow then populates the scaffold with per-vertex latent tokens, conditioned on the image, the scaffold, and a requested vertex budget. This design delivers three practical capabilities: interactive generation speed through parallel flow-based synthesis; effective face-count control through the requested vertex budget; and native support for multi-part assets, whose components emerge directly from the generated connectivity. In our experiments, Meshy T2 achieves state-of-the-art geometric fidelity and completes end-to-end image-to-mesh generation within a median of 6 seconds, over an order of magnitude faster than autoregressive baselines. Code and weights will be available at https://github.com/meshy-dev/meshy-t2.

arXiv

Understanding Knowledge Transfer Mechanism in Heterogeneous MLLM Fusion: A Simple Linear Approach

Yinghao Hou, Jiahe Fan, Yuanhao Pu, Zongyuan Chen, Hong Xie

Training-free fusion of heterogeneous multimodal large language models (MLLMs) provides a direct route for cross-scale capability transfer, yet improvements in aggregate performance do not reveal what a smaller model actually inherits. Existing studies are largely designed and evaluated on limited task sets or aggregate metrics; as evaluation expands to broader task collections, whether different capabilities can transfer across scales remains poorly understood. To investigate this question, we introduce Cross-Scale Directional Parameter Injection (CDPI), a simple linear probe to analyze cross-scale knowledge transfer during heterogeneous fusion. A local theoretical analysis indicates that knowledge transfer selectivity is determined at first order by capability-dependent responses to a shared injection direction, while second-order curvature effects constrain the effective transfer regime. Across four Qwen3-VL model pairs and twelve multimodal benchmarks, our experiments reveal a consistent pattern of selectivity: gains concentrate on reasoning, particularly high-level reasoning, whereas perception performance remains close to that of the original target model. Component-wise ablations further show that high-level reasoning gains arise primarily from the language model, while ratio analysis finds that positive selective transfer occurs mainly in the small-ratio regime. These findings recast cross-scale heterogeneous MLLM fusion as selective language-side reasoning transfer within a narrow, low-interference regime, rather than broad capability inheritance.

arXiv

Pixel-Space Diffusion Transformers

Renye Yan, Jikang Cheng, You Wu, Ling Liang, Wei Peng, Athanasios V. Vasilakos, Qingyu Zhao, Yu Zhang, Yimao Cai, Kilian M. Pohl, Guoying Zhao

Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space. However, fixed visual tokenizers can discard fine textures and structural details, while separate representation and diffusion training creates a mismatch between reconstruction and generation objectives. These limitations have renewed interest in pixel-space diffusion, which models raw pixels directly, removes the VAE bottleneck, and supports end-to-end optimization. This formulation better matches the demands of high-fidelity generation but introduces challenges in high-dimensional modeling, including noise scheduling, loss weighting, token efficiency, and scalable architecture design. Pixel-space modeling also offers a promising basis for unified multimodal systems: raw pixels, text, and task conditions can be represented in a shared token space and jointly processed by a single Transformer, narrowing the gap between visual understanding and generation. This paper reviews Pixel-Space Diffusion Transformers (pDiTs) from the perspectives of model architecture, continuous generative mechanisms, and unified multimodal modeling. We summarize representative methods, identify key technical challenges, and discuss future directions toward high-fidelity, end-to-end vision foundation models that integrate generation and understanding.

arXiv

SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers

Minghao Yin, Jiahao Lu, Wenbo Hu, Wang Zhao, Shan Ying, Kai Han

Video diffusion transformers address their tokens by position on the pixel-time grid: an address in the tensor, not in the world. The address we would want, the world point a token depicts, lies on a surface not yet generated, while its camera ray is fixed once the user specifies a trajectory. SCoPE therefore treats the ray as a second positional coordinate, and camera control becomes a property of the coordinate system, not an added module. The ray is added to the pretrained attention's queries and keys, and the score gains a term that reads the two rays alone. Its canonical form, the reciprocal product of line geometry, measures how nearly two lines of sight meet. Normalize-Gate-Inject makes a single encoding trainable across metric and up-to-scale pose sources. The retrofit keeps RoPE bit-exact, starts from the unchanged pretrained DiT, and adds under 0.1/% new parameters. On Wan2.2 at 5B and 14B under matched data and budget, SCoPE improves every camera-controllability and fidelity metric, leads all closed-loop revisit metrics, and shows widening margins with model size. At 14B, rotation error falls 29/% and FVD 43/% below the strongest baseline.

arXiv

Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs

Wenjie Zhu, Yabin ZHANG, Liang Xu, Xin Jin, Wenjun Zeng, Lei Zhang

While test-time adaptation (TTA) empowers vision-language models to adapt without costly retraining, it remains highly vulnerable to out-of-distribution (OOD) outliers prevalent in real-world applications. This discrepancy motivates Noisy TTA (NTTA), an online task to filter noisy OOD samples on the fly while maximizing in-distribution (ID) classification accuracy. Existing zero-shot NTTA approaches typically rely on test-time discriminative training, leading to overconfident misclassifications and significantly degraded inference efficiency. To address these limitations, we propose a novel framework named Dual Distribution Estimation (DDE), shifting the zero-shot NTTA paradigm from instance-level learning to training-free Gaussian distribution modeling. DDE incorporates two novel modules: Positive Feature Distribution Estimation (PFDE) and Negative Label Distribution Estimation (NLDE). PFDE explicitly models class-wise inclusion and exclusion Gaussian distributions to formulate a calibrated contrastive score, robustly enhancing ID accuracy. In parallel, NLDE improves OOD identification by explicitly modeling the negative label distribution to mine highly discriminative labels, effectively mitigating spurious correlations. Extensive experiments show that on the large-scale ImageNet benchmark, DDE achieves an improvement of 3.70\% in harmonic mean accuracy and reduces the FPR95 for OOD detection by 6.20\%, while ensuring highly scalable and efficient online inference. Furthermore, DDE is zero-shot and training-free, demonstrating remarkable robustness in data-scarce scenarios. Codes are available at https://github.com/ZhuWenjie98/DDE.

arXiv

Vision-Reasoning-Guided Occlusion Removal from Light Fields

Mohamed Youssef, Oliver Bimber

Occlusion-robust scene recovery remains a major challenge in computational imaging, particularly where dense vegetation severely limits visibility. We propose a visionreasoning-guided light field occlusion removal framework combining light field integration (LFI) with vision-language model (VLM) semantic reasoning. Multi-view observations are first integrated via LFI to suppress foreground occlusions, producing an initial visibility-enhanced representation, a VLM then acts as a conditional semantic prior to restore degraded structures and fine details. A multi-sample fusion strategy aggregates multiple generated hypotheses to improve consistency and reduce hallucination. Experimental results on synthetic and real-world datasets show state-of-the-art performance, achieving the highest average SSIM across four synthetic benchmark scenes (4-Syn) and strong generalization across structured and unstructured acquisition settings, with applicability to search-and-rescue and exploratory robotic navigation.

arXiv

MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation

Xingyuming Liu, Ruichun Ma, Heyu Guo, Qixiu Li, Qingwen Yang, Lin Luo, Shiqi Jiang, Chenren Xu, Jiaolong Yang, Baining Guo

Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for robotics rely solely on RGB observations. This limits their ability to perceive physical properties that are difficult or impossible to infer from RGB cameras, such as temperature, sound, or radar response. We present MuseVLA, an adaptive multimodal sensing VLA model that integrates novel sensors as on-demand tools for robotic manipulation. Given a task instruction and visual context, MuseVLA first generates a sensor token and target description that select the sensing modality to invoke and what to attend to, analogous to a tool call with arguments. It then converts the selected sensor measurement into a grounded sensor image, a unified intermediate representation that encodes heterogeneous readings for multimodal fusion and action generation. This design decouples sensor-specific processing from the VLA backbone, enabling efficient integration of diverse modalities. To reduce the need for expensive multisensory robot datasets, we further introduce a data synthesis pipeline that augments existing RGB video datasets with grounded sensor images, enabling generalization to unseen sensor-guided tasks. We evaluate MuseVLA on a real-world robot across challenging dexterous hand manipulation tasks that require multimodal sensing inputs, including temperature-guided pick-and-place, audio-driven object search, and radar-assisted hidden object retrieval. MuseVLA achieves 80.6% success rate on average, outperforming RGB-only and multisensory VLA baselines significantly, and exhibits strong zero-shot capabilities on unseen tasks. Code, model and dataset are available at https://github.com/microsoft/MuseVLA.

arXiv

Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association

Matvei Shelukhan, Timur Mamedov, Aleksandr Chukhrov, Karina Kvanchiani

Multi-view object association is an important computer vision problem that underlies many multi-camera perception tasks. While this task is naturally formulated as a constrained one-to-one matching problem, recent works heavily rely on pairwise ranking metrics like AP and FPR-95 for model evaluation. We highlight a fundamental mismatch between these metrics and the actual assignment objective. Theoretically, we show that AP and FPR-95 can be imperfect even when the assignment is already correct, and that Sinkhorn-based normalization can make them perfect. Conversely, optimal pairwise ranking can still lead to incorrect assignments. We validate this mismatch in practice by using our Sinkhorn-based normalization as a controlled post-processing stress test. We show that optimizing just a few post-processing parameters significantly boosts AP and FPR-95 without corresponding improvements in assignment-level metrics such as ACC and IPAA.

arXiv

CalibAnyView: Beyond Single-View Camera Calibration in the Wild

Boying Li, Cheng Zhang, Weirong Chen, Guyuan Chen, Daniel Cremers, Jianfei Cai, Ian Reid, Hamid Rezatofighi

Camera calibration is fundamental to reliable geometric perception, yet classical approaches rely on dedicated targets, successful reconstruction, or dense view coverage, which casually captured imagery rarely satisfies. Recent learning-based single-image methods lift these requirements by exploiting visual cues, and extend calibration beyond intrinsics to gravity estimation. Yet in the common multi-view case, they predict each view independently and combine the estimates only afterwards, lacking full use of cross-view consistency. We bridge this gap with CalibAnyView, a framework that unifies single- and sparse multi-view calibration by enforcing that consistency inside the network: a transformer with cross-view attention predicts camera-model-agnostic perspective fields, followed by a multi-view optimization that fuses them into shared intrinsics and per-view gravity directions, covering camera models from pinhole to severely distorted lenses. To support this, we construct a large-scale in-the-wild multi-view video dataset spanning diverse camera models, dynamic scenes, realistic motion trajectories, and heterogeneous lens distortions. Extensive experiments show that CalibAnyView outperforms state-of-the-art methods in both sparse multi-view and single-view settings spanning pinhole to distorted optics.

arXiv

Hyper-FSAD: Training-Free and Language-Free Few-Shot Anomaly Detection via Sparse Hyper Matching

Guohuan Xie, Xin He, Dingying Fan, Siqi Li, Yun Liu

Few-shot anomaly detection (FSAD) is particularly valuable when only a few normal images are available in a new target domain, while anomalous cases are rare, diverse, and difficult to enumerate in advance. However, existing methods often still require task-specific fitting or language prompts, and their patch-level retrieval commonly relies on brittle nearest-neighbor or fixed Top-$p$ rules. We propose \textbf{Hyper-FSAD}, a training-free and language-free framework that performs support-only inference with a frozen visual encoder. We formulate FSAD as support-only scoring in frozen feature space and establish the selective stability of sparse retrieval and sufficient conditions for normal--anomaly separation. Guided by this analysis, \textbf{Sparse Hyper Matching} uses \textit{sparsemax} to adaptively select support patches for each query patch, exactly suppressing below-threshold distractors without a manually specified retrieval hyperparameter. \textbf{Dual-Branch Image Scoring} further combines local reconstruction discrepancies with support-conditioned global <CLS> deviation. Across four industrial and two medical benchmarks, Hyper-FSAD achieves the best overall performance across the 1/2/4-shot settings, while requiring only 52.6\,ms per image and 0.89\,GB GPU memory. The code will be released.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.