Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments

• URL: http://arxiv.org/abs/2403.13803v1
• Date: Wed, 20 Mar 2024 17:59:16 GMT
• Title: Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
• Authors: Yang Yang, Wenhai Wang, Zhe Chen, Jifeng Dai, Liang Zheng,
• Abstract summary: Good detectors tend to output bounding boxes whose locations do not change much, while bounding boxes of poor detectors will undergo noticeable position changes. We compute the box stability score (BoS score) to reflect this stability. We contribute to finding that BoS score has a strong, positive correlation with detection accuracy measured by mean average precision (mAP) under various test environments.
• Score: 52.65013932553849
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bounding boxes uniquely characterize object detection, where a good detector gives accurate bounding boxes of categories of interest. However, in the real-world where test ground truths are not provided, it is non-trivial to find out whether bounding boxes are accurate, thus preventing us from assessing the detector generalization ability. In this work, we find under feature map dropout, good detectors tend to output bounding boxes whose locations do not change much, while bounding boxes of poor detectors will undergo noticeable position changes. We compute the box stability score (BoS score) to reflect this stability. Specifically, given an image, we compute a normal set of bounding boxes and a second set after feature map dropout. To obtain BoS score, we use bipartite matching to find the corresponding boxes between the two sets and compute the average Intersection over Union (IoU) across the entire test set. We contribute to finding that BoS score has a strong, positive correlation with detection accuracy measured by mean average precision (mAP) under various test environments. This relationship allows us to predict the accuracy of detectors on various real-world test sets without accessing test ground truths, verified on canonical detection tasks such as vehicle detection and pedestrian detection. Code and data are available at https://github.com/YangYangGirl/BoS.

Related papers

• Deployment Prior Injection for Run-time Calibratable Object Detection [58.636806402337776]
  We introduce an additional graph input to the detector, where the graph represents the deployment context prior. During the test phase, any suitable deployment context prior can be injected into the detector via graph edits. Even if the deployment prior is unknown, the detector can self-calibrate using deployment prior approximated using its own predictions.
  arXiv  Detail & Related papers  (2024-02-27T04:56:04Z)
• Semi-DETR: Semi-Supervised Object Detection with Detection Transformers [105.45018934087076]
  We analyze the DETR-based framework on semi-supervised object detection (SSOD) We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector. Our method outperforms all state-of-the-art methods by clear margins.
  arXiv  Detail & Related papers  (2023-07-16T16:32:14Z)
• ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing [32.679280923208715]
  Unsupervised Domain Adaptation (UDA) for object detection aims to adapt a model trained on a source domain to detect instances from a new target domain for which annotations are not available. We propose ConfMix, the first method that introduces a sample mixing strategy based on region-level detection confidence for adaptive object detector learning.
  arXiv  Detail & Related papers  (2022-10-20T19:16:39Z)
• Dynamic Label Assignment for Object Detection by Combining Predicted and Anchor IoUs [20.41563386339572]
  We introduce a simple and effective approach to perform label assignment dynamically based on the training status with predictions. Our approach shows improvements in the performance of the detection models with the adaptive label assignment algorithm.
  arXiv  Detail & Related papers  (2022-01-23T23:14:07Z)
• Reference-based Defect Detection Network [57.89399576743665]
  The first issue is the texture shift which means a trained defect detector model will be easily affected by unseen texture. The second issue is partial visual confusion which indicates that a partial defect box is visually similar with a complete box. We propose a Reference-based Defect Detection Network (RDDN) to tackle these two problems.
  arXiv  Detail & Related papers  (2021-08-10T05:44:23Z)
• Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections [50.096540945099704]
  We propose a novel ensemble called the Probabilistic Ranking Aware Ensemble (PRAE) that refines the confidence of bounding boxes from detectors. We also introduce a bandit approach to address the confidence imbalance problem caused by the need to deal with different numbers of boxes.
  arXiv  Detail & Related papers  (2021-05-07T09:37:06Z)
• Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detection [70.25977409196449]
  False positive is one of the most serious problems brought by domain shift in domain adaptive pedestrian detection. We transform a false positive suppression problem into a box re-ranking problem elegantly. Considering we aim to keep the detection of true positive unchanged, we propose box number alignment.
  arXiv  Detail & Related papers  (2021-02-01T02:31:11Z)
• 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)

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.