Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild

• URL: http://arxiv.org/abs/2203.03800v1
• Date: Tue, 8 Mar 2022 01:44:03 GMT
• Title: Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild
• Authors: Xuefeng Du, Xin Wang, Gabriel Gozum, Yixuan Li
• Abstract summary: We propose a new unknown-aware object detection framework through Spatial-Temporal Unknown Distillation (STUD) STUD distills unknown objects from videos in the wild and meaningfully regularizes the model's decision boundary. We establish the state-of-the-art performance on OOD detection tasks for object detection, reducing the FPR95 score by over 10% compared to the previous best method.
• Score: 29.155394550694197
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building reliable object detectors that can detect out-of-distribution (OOD) objects is critical yet underexplored. One of the key challenges is that models lack supervision signals from unknown data, producing overconfident predictions on OOD objects. We propose a new unknown-aware object detection framework through Spatial-Temporal Unknown Distillation (STUD), which distills unknown objects from videos in the wild and meaningfully regularizes the model's decision boundary. STUD first identifies the unknown candidate object proposals in the spatial dimension, and then aggregates the candidates across multiple video frames to form a diverse set of unknown objects near the decision boundary. Alongside, we employ an energy-based uncertainty regularization loss, which contrastively shapes the uncertainty space between the in-distribution and distilled unknown objects. STUD establishes the state-of-the-art performance on OOD detection tasks for object detection, reducing the FPR95 score by over 10% compared to the previous best method. Code is available at https://github.com/deeplearning-wisc/stud.

Related papers

• Bayesian Detector Combination for Object Detection with Crowdsourced Annotations [49.43709660948812]
  Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise. We propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations. BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models.
  arXiv  Detail & Related papers  (2024-07-10T18:00:54Z)
• 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)
• Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments [67.83787474506073]
  We tackle the limitations of current LiDAR-based 3D object detection systems. We introduce a universal textscFind n' Propagate approach for 3D OV tasks. We achieve up to a 3.97-fold increase in Average Precision (AP) for novel object classes.
  arXiv  Detail & Related papers  (2024-03-20T12:51:30Z)
• Unsupervised Recognition of Unknown Objects for Open-World Object Detection [28.787586991713535]
  Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario. Current OWOD models, such as ORE and OW-DETR, focus on pseudo-labeling regions with high objectness scores as unknowns. This paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects.
  arXiv  Detail & Related papers  (2023-08-31T08:17:29Z)
• 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)
• Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects [21.426594215463105]
  We propose the unknown sniffer (UnSniffer) to find both unknown and known objects. GOC score is introduced, which only uses known samples for supervision and avoids improper suppression of unknowns in the background. We present the Unknown Object Detection Benchmark, the first publicly benchmark that encompasses precision evaluation for unknown detection to our knowledge.
  arXiv  Detail & Related papers  (2023-03-24T02:59:44Z)
• PROB: Probabilistic Objectness for Open World Object Detection [15.574535196804042]
  Open World Object Detection (OWOD) is a new computer vision task that bridges the gap between classic object detection (OD) benchmarks and object detection in the real world. We introduce a novel probabilistic framework for objectness estimation, where we alternate between probability distribution estimation and objectness likelihood of known objects. The resulting Probabilistic Objectness transformer-based open-world detector, PROB, integrates our framework into traditional object detection models.
  arXiv  Detail & Related papers  (2022-12-02T20:04:24Z)
• More Practical Scenario of Open-set Object Detection: Open at Category Level and Closed at Super-category Level [23.98839374194848]
  Open-set object detection (OSOD) has recently attracted considerable attention. We first point out that the scenario of OSOD considered in recent studies, which considers an unlimited variety of unknown objects, has a fundamental issue. This issue leads to difficulty with the evaluation of methods' performance on unknown object detection.
  arXiv  Detail & Related papers  (2022-07-20T09:28:51Z)
• OW-DETR: Open-world Detection Transformer [90.56239673123804]
  We introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection. OW-DETR comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification and objectness scoring. Our model outperforms the recently introduced OWOD approach, ORE, with absolute gains ranging from 1.8% to 3.3% in terms of unknown recall.
  arXiv  Detail & Related papers  (2021-12-02T18:58:30Z)
• 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)

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.