Quantization Robustness to Input Degradations for Object Detection

Post-training quantization (PTQ) is crucial for deploying efficient object detection models, like YOLO, on resource-constrained devices. However, the impact of reduced precision on model robustness to real-world input degradations such as noise, blur, and compression artifacts is a significant concern. This paper presents a comprehensive empirical study evaluating the robustness of YOLO models (nano to extra-large scales) across multiple precision formats: FP32, FP16 (TensorRT), Dynamic UINT8 (ONNX), and Static INT8 (TensorRT). We introduce and evaluate a degradation-aware calibration strategy for Static INT8 PTQ, where the TensorRT calibration process is exposed to a mix of clean and synthetically degraded images. Models were benchmarked on the COCO dataset under seven distinct degradation conditions (including various types and levels of noise, blur, low contrast, and JPEG compression) and a mixed-degradation scenario. Results indicate that while Static INT8 TensorRT engines offer substantial speedups (~1.5-3.3x) with a moderate accuracy drop (~3-7% mAP50-95) on clean data, the proposed degradation-aware calibration did not yield consistent, broad improvements in robustness over standard clean-data calibration across most models and degradations. A notable exception was observed for larger model scales under specific noise conditions, suggesting model capacity may influence the efficacy of this calibration approach. These findings highlight the challenges in enhancing PTQ robustness and provide insights for deploying quantized detectors in uncontrolled environments. All code and evaluation tables are available at https://github.com/AllanK24/QRID.

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models

Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual information, the choice of visual encoder is pivotal. We hypothesize that the diverse training paradigms employed by different visual encoders instill them with distinct inductive biases, which leads to their diverse hallucination performances. Existing benchmarks typically focus on coarse-grained hallucination detection and fail to capture the diverse hallucinations elaborated in our hypothesis. To systematically analyze these effects, we introduce VHBench-10, a comprehensive benchmark with approximately 10,000 samples for evaluating LVLMs across ten fine-grained hallucination categories. Our evaluations confirm encoders exhibit unique hallucination characteristics. Building on these insights and the suboptimality of simple feature fusion, we propose VisionWeaver, a novel Context-Aware Routing Network. It employs global visual features to generate routing signals, dynamically aggregating visual features from multiple specialized experts. Comprehensive experiments confirm the effectiveness of VisionWeaver in significantly reducing hallucinations and improving overall model performance.

Dual-Stage Reweighted MoE for Long-Tailed Egocentric Mistake Detection

In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data. To handle the challenges posed by subtle and infrequent mistakes, we propose a Dual-Stage Reweighted Mixture-of-Experts (DR-MoE) framework. In the first stage, features are extracted using a frozen ViViT model and a LoRA-tuned ViViT model, which are combined through a feature-level expert module. In the second stage, three classifiers are trained with different objectives: reweighted cross-entropy to mitigate class imbalance, AUC loss to improve ranking under skewed distributions, and label-aware loss with sharpness-aware minimization to enhance calibration and generalization. Their predictions are fused using a classification-level expert module. The proposed method achieves strong performance, particularly in identifying rare and ambiguous mistake instances. The code is available at https://github.com/boyuh/DR-MoE.

Self-supervised structured object representation learning

Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured representation in scenes. In this work, we propose a self-supervised approach that progressively builds structured visual representations by combining semantic grouping, instance level separation, and hierarchical structuring. Our approach, based on a novel ProtoScale module, captures visual elements across multiple spatial scales. Unlike common strategies like DINO that rely on random cropping and global embeddings, we preserve full scene context across augmented views to improve performance in dense prediction tasks. We validate our method on downstream object detection tasks using a combined subset of multiple datasets (COCO and UA-DETRAC). Experimental results show that our method learns object centric representations that enhance supervised object detection and outperform the state-of-the-art methods, even when trained with limited annotated data and fewer fine-tuning epochs.

FusionCounting: Robust visible-infrared image fusion guided by crowd counting via multi-task learning

Most visible and infrared image fusion (VIF) methods focus primarily on optimizing fused image quality. Recent studies have begun incorporating downstream tasks, such as semantic segmentation and object detection, to provide semantic guidance for VIF. However, semantic segmentation requires extensive annotations, while object detection, despite reducing annotation efforts compared with segmentation, faces challenges in highly crowded scenes due to overlapping bounding boxes and occlusion. Moreover, although RGB-T crowd counting has gained increasing attention in recent years, no studies have integrated VIF and crowd counting into a unified framework. To address these challenges, we propose FusionCounting, a novel multi-task learning framework that integrates crowd counting into the VIF process. Crowd counting provides a direct quantitative measure of population density with minimal annotation, making it particularly suitable for dense scenes. Our framework leverages both input images and population density information in a mutually beneficial multi-task design. To accelerate convergence and balance tasks contributions, we introduce a dynamic loss function weighting strategy. Furthermore, we incorporate adversarial training to enhance the robustness of both VIF and crowd counting, improving the model's stability and resilience to adversarial attacks. Experimental results on public datasets demonstrate that FusionCounting not only enhances image fusion quality but also achieves superior crowd counting performance.

OVGrasp: Open-Vocabulary Grasping Assistance via Multimodal Intent Detection

Grasping assistance is essential for restoring autonomy in individuals with motor impairments, particularly in unstructured environments where object categories and user intentions are diverse and unpredictable. We present OVGrasp, a hierarchical control framework for soft exoskeleton-based grasp assistance that integrates RGB-D vision, open-vocabulary prompts, and voice commands to enable robust multimodal interaction. To enhance generalization in open environments, OVGrasp incorporates a vision-language foundation model with an open-vocabulary mechanism, allowing zero-shot detection of previously unseen objects without retraining. A multimodal decision-maker further fuses spatial and linguistic cues to infer user intent, such as grasp or release, in multi-object scenarios. We deploy the complete framework on a custom egocentric-view wearable exoskeleton and conduct systematic evaluations on 15 objects across three grasp types. Experimental results with ten participants demonstrate that OVGrasp achieves a grasping ability score (GAS) of 87.00%, outperforming state-of-the-art baselines and achieving improved kinematic alignment with natural hand motion.

Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation

Feature foundation models - usually vision transformers - offer rich semantic descriptors of images, useful for downstream tasks such as (interactive) segmentation and object detection. For computational efficiency these descriptors are often patch-based, and so struggle to represent the fine features often present in micrographs; they also struggle with the large image sizes present in materials and biological image analysis. In this work, we train a convolutional neural network to upsample low-resolution (i.e, large patch size) foundation model features with reference to the input image. We apply this upsampler network (without any further training) to efficiently featurise and then segment a variety of microscopy images, including plant cells, a lithium-ion battery cathode and organic crystals. The richness of these upsampled features admits separation of hard to segment phases, like hairline cracks. We demonstrate that interactive segmentation with these deep features produces high-quality segmentations far faster and with far fewer labels than training or finetuning a more traditional convolutional network.

Context-aware Sparse Spatiotemporal Learning for Event-based Vision

Event-based camera has emerged as a promising paradigm for robot perception, offering advantages with high temporal resolution, high dynamic range, and robustness to motion blur. However, existing deep learning-based event processing methods often fail to fully leverage the sparse nature of event data, complicating their integration into resource-constrained edge applications. While neuromorphic computing provides an energy-efficient alternative, spiking neural networks struggle to match of performance of state-of-the-art models in complex event-based vision tasks, like object detection and optical flow. Moreover, achieving high activation sparsity in neural networks is still difficult and often demands careful manual tuning of sparsity-inducing loss terms. Here, we propose Context-aware Sparse Spatiotemporal Learning (CSSL), a novel framework that introduces context-aware thresholding to dynamically regulate neuron activations based on the input distribution, naturally reducing activation density without explicit sparsity constraints. Applied to event-based object detection and optical flow estimation, CSSL achieves comparable or superior performance to state-of-the-art methods while maintaining extremely high neuronal sparsity. Our experimental results highlight CSSL's crucial role in enabling efficient event-based vision for neuromorphic processing.

PointAD+: Learning Hierarchical Representations for Zero-shot 3D Anomaly Detection

In this paper, we aim to transfer CLIP's robust 2D generalization capabilities to identify 3D anomalies across unseen objects of highly diverse class semantics. To this end, we propose a unified framework to comprehensively detect and segment 3D anomalies by leveraging both point- and pixel-level information. We first design PointAD, which leverages point-pixel correspondence to represent 3D anomalies through their associated rendering pixel representations. This approach is referred to as implicit 3D representation, as it focuses solely on rendering pixel anomalies but neglects the inherent spatial relationships within point clouds. Then, we propose PointAD+ to further broaden the interpretation of 3D anomalies by introducing explicit 3D representation, emphasizing spatial abnormality to uncover abnormal spatial relationships. Hence, we propose G-aggregation to involve geometry information to enable the aggregated point representations spatially aware. To simultaneously capture rendering and spatial abnormality, PointAD+ proposes hierarchical representation learning, incorporating implicit and explicit anomaly semantics into hierarchical text prompts: rendering prompts for the rendering layer and geometry prompts for the geometry layer. A cross-hierarchy contrastive alignment is further introduced to promote the interaction between the rendering and geometry layers, facilitating mutual anomaly learning. Finally, PointAD+ integrates anomaly semantics from both layers to capture the generalized anomaly semantics. During the test, PointAD+ can integrate RGB information in a plug-and-play manner and further improve its detection performance. Extensive experiments demonstrate the superiority of PointAD+ in ZS 3D anomaly detection across unseen objects with highly diverse class semantics, achieving a holistic understanding of abnormality.

Beyond Marginals: Learning Joint Spatio-Temporal Patterns for Multivariate Anomaly Detection

In this paper, we aim to improve multivariate anomaly detection (AD) by modeling the \textit{time-varying non-linear spatio-temporal correlations} found in multivariate time series data . In multivariate time series data, an anomaly may be indicated by the simultaneous deviation of interrelated time series from their expected collective behavior, even when no individual time series exhibits a clearly abnormal pattern on its own. In many existing approaches, time series variables are assumed to be (conditionally) independent, which oversimplifies real-world interactions. Our approach addresses this by modeling joint dependencies in the latent space and decoupling the modeling of \textit{marginal distributions, temporal dynamics, and inter-variable dependencies}. We use a transformer encoder to capture temporal patterns, and to model spatial (inter-variable) dependencies, we fit a multi-variate likelihood and a copula. The temporal and the spatial components are trained jointly in a latent space using a self-supervised contrastive learning objective to learn meaningful feature representations to separate normal and anomaly samples.