Revisiting Out-of-Distribution Detection in Real-time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigm

• URL: http://arxiv.org/abs/2503.07330v3
• Date: Wed, 20 Aug 2025 21:24:44 GMT
• Title: Revisiting Out-of-Distribution Detection in Real-time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigm
• Authors: Changshun Wu, Weicheng He, Chih-Hong Cheng, Xiaowei Huang, Saddek Bensalem,
• Abstract summary: Out-of-distribution (OoD) inputs pose a persistent challenge to deep learning models.<n>This work addresses two overlooked dimensions of OoD detection in object detection.<n>We introduce a novel training-time mitigation paradigm that operates independently of external OoD detectors.
• Score: 8.206992765692535
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Out-of-distribution (OoD) inputs pose a persistent challenge to deep learning models, often triggering overconfident predictions on non-target objects. While prior work has primarily focused on refining scoring functions and adjusting test-time thresholds, such algorithmic improvements offer only incremental gains. We argue that a rethinking of the entire development lifecycle is needed to mitigate these risks effectively. This work addresses two overlooked dimensions of OoD detection in object detection. First, we reveal fundamental flaws in widely used evaluation benchmarks: contrary to their design intent, up to 13% of objects in the OoD test sets actually belong to in-distribution classes, and vice versa. These quality issues severely distort the reported performance of existing methods and contribute to their high false positive rates. Second, we introduce a novel training-time mitigation paradigm that operates independently of external OoD detectors. Instead of relying solely on post-hoc scoring, we fine-tune the detector using a carefully synthesized OoD dataset that semantically resembles in-distribution objects. This process shapes a defensive decision boundary by suppressing objectness on OoD objects, leading to a 91% reduction in hallucination error of a YOLO model on BDD-100K. Our methodology generalizes across detection paradigms such as YOLO, Faster R-CNN, and RT-DETR, and supports few-shot adaptation. Together, these contributions offer a principled and effective way to reduce OoD-induced hallucination in object detectors. Code and data are available at: https://gricad-gitlab.univ-grenoble-alpes.fr/dnn-safety/m-hood.

Related papers

• A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection [13.109309606764754]
  We introduce a plug-in detection framework that leverages internal layer-wise inconsistencies within the target model itself.<n>Our method achieves state-of-the-art detection performance with negligible computational overhead.
  arXiv  Detail & Related papers  (2025-05-19T00:48:53Z)
• Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detection [73.85890512959861]
  We propose a task-agnostic framework to unify Salient Object Detection (SOD) and Camouflaged Object Detection (COD)<n>We design a simple yet effective contextual decoder involving the interval-layer and global context, which achieves an inference speed of 67 fps.<n> Experiments on public SOD and COD datasets demonstrate the superiority of our proposed framework in both supervised and unsupervised settings.
  arXiv  Detail & Related papers  (2024-12-22T03:25:43Z)
• Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning [51.170479006249195]
  We introduce a new dataset, benchmark, and a dynamic coarse-to-fine learning scheme in this study.<n>Our proposed dataset, AI-TOD-R, features the smallest object sizes among all oriented object detection datasets.<n>We present a benchmark spanning a broad range of detection paradigms, including both fully-supervised and label-efficient approaches.
  arXiv  Detail & Related papers  (2024-12-16T09:14:32Z)
• On the Inherent Robustness of One-Stage Object Detection against Out-of-Distribution Data [6.267143531261792]
  We propose a novel detection algorithm for detecting unknown objects in image data.<n>It exploits supervised dimensionality reduction techniques to mitigate the effects of the curse of dimensionality on the features extracted by the model.<n>It utilizes high-resolution feature maps to identify potential unknown objects in an unsupervised fashion.
  arXiv  Detail & Related papers  (2024-11-07T10:15:25Z)
• Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detection [12.633311483061647]
  Out-of-distribution (OOD) objects can lead to misclassifications, posing a significant risk to the safety and reliability of automated vehicles. We propose a new evaluation protocol that allows the use of existing datasets without modifying the point cloud. The effectiveness of our method is validated through experiments on the newly proposed nuScenes OOD benchmark.
  arXiv  Detail & Related papers  (2024-04-24T13:48:38Z)
• Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection [12.417754433715903]
  We introduce Sparse Semi-DETR, a novel transformer-based, end-to-end semi-supervised object detection solution. Sparse Semi-DETR incorporates a Query Refinement Module to enhance the quality of object queries, significantly improving detection capabilities for small and partially obscured objects. On the MS-COCO and Pascal VOC object detection benchmarks, Sparse Semi-DETR achieves a significant improvement over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-04-02T10:22:23Z)
• SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection [53.19618419772467]
  Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds. With the development of Transformer, the scale of SIRST models is constantly increasing. With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
  arXiv  Detail & Related papers  (2024-03-08T16:14:54Z)
• Object-Centric Multiple Object Tracking [124.30650395969126]
  This paper proposes a video object-centric model for multiple-object tracking pipelines. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module. Benefited from object-centric learning, we only require sparse detection labels for object localization and feature binding.
  arXiv  Detail & Related papers  (2023-09-01T03:34:12Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Wasserstein distributional robustness of neural networks [9.79503506460041]
  Deep neural networks are known to be vulnerable to adversarial attacks (AA) For an image recognition task, this means that a small perturbation of the original can result in the image being misclassified. We re-cast the problem using techniques of Wasserstein distributionally robust optimization (DRO) and obtain novel contributions.
  arXiv  Detail & Related papers  (2023-06-16T13:41:24Z)
• SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving [160.57870373052577]
  We propose a saliency-based OD algorithm (SalienDet) to detect unknown objects. Our SalienDet utilizes a saliency-based algorithm to enhance image features for object proposal generation. We design a dataset relabeling approach to differentiate the unknown objects from all objects in training sample set to achieve Open-World Detection.
  arXiv  Detail & Related papers  (2023-05-11T16:19:44Z)
• SOOD: Towards Semi-Supervised Oriented Object Detection [57.05141794402972]
  This paper proposes a novel Semi-supervised Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework. Our experiments show that when trained with the two proposed losses, SOOD surpasses the state-of-the-art SSOD methods under various settings on the DOTA-v1.5 benchmark.
  arXiv  Detail & Related papers  (2023-04-10T11:10:42Z)
• A Tri-Layer Plugin to Improve Occluded Detection [100.99802831241583]
  We propose a simple '' module for the detection head of two-stage object detectors to improve the recall of partially occluded objects. The module predicts a tri-layer of segmentation masks for the target object, the occluder and the occludee, and by doing so is able to better predict the mask of the target object. We also establish a COCO evaluation dataset to measure the recall performance of partially occluded and separated objects.
  arXiv  Detail & Related papers  (2022-10-18T17:59:51Z)
• SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection [10.306996649145464]
  We show that residual convolutional layers with batch normalisation produce Sensitivity-Aware FEatures (SAFE) SAFE is consistently powerful for distinguishing in-distribution from out-of-distribution detections. We extract SAFE vectors for every detected object, and train a multilayer perceptron on the surrogate task of distinguishing adversarially perturbed from clean in-distribution examples.
  arXiv  Detail & Related papers  (2022-08-29T23:57:55Z)
• Benchmarking Deep Models for Salient Object Detection [67.07247772280212]
  We construct a general SALient Object Detection (SALOD) benchmark to conduct a comprehensive comparison among several representative SOD methods. In the above experiments, we find that existing loss functions usually specialized in some metrics but reported inferior results on the others. We propose a novel Edge-Aware (EA) loss that promotes deep networks to learn more discriminative features by integrating both pixel- and image-level supervision signals.
  arXiv  Detail & Related papers  (2022-02-07T03:43:16Z)
• Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images [15.404024559652534]
  We present an effective Dynamic Enhancement Anchor (DEA) network to construct a novel training sample generator. Our method achieves state-of-the-art performance in accuracy with moderate inference speed and computational overhead for training.
  arXiv  Detail & Related papers  (2021-12-13T14:37:20Z)
• Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection [26.008419879970365]
  In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model. Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality. We propose Jaccard IoU as a new evaluation metric that extends IoU by incorporating label uncertainty.
  arXiv  Detail & Related papers  (2020-12-18T09:11:44Z)
• Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation [7.305019142196585]
  "Out-of-distribution" (OoD) samples are crucial for many applications such as automated driving. A natural baseline approach to OoD detection is to threshold on the pixel-wise softmax entropy. We present a two-step procedure that significantly improves that approach.
  arXiv  Detail & Related papers  (2020-12-09T11:01:06Z)
• Slender Object Detection: Diagnoses and Improvements [74.40792217534]
  In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects. For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
  arXiv  Detail & Related papers  (2020-11-17T09:39:42Z)
• Detection as Regression: Certified Object Detection by Median Smoothing [50.89591634725045]
  This work is motivated by recent progress on certified classification by randomized smoothing. We obtain the first model-agnostic, training-free, and certified defense for object detection against $ell$-bounded attacks.
  arXiv  Detail & Related papers  (2020-07-07T18:40:19Z)
• SESS: Self-Ensembling Semi-Supervised 3D Object Detection [138.80825169240302]
  We propose SESS, a self-ensembling semi-supervised 3D object detection framework. Specifically, we design a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data. Our SESS achieves competitive performance compared to the state-of-the-art fully-supervised method by using only 50% labeled data.
  arXiv  Detail & Related papers  (2019-12-26T08:48:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.