Boundary Distribution Estimation for Precise Object Detection

• URL: http://arxiv.org/abs/2111.01396v2
• Date: Wed, 19 Jul 2023 08:55:05 GMT
• Title: Boundary Distribution Estimation for Precise Object Detection
• Authors: Peng Zhi, Haoran Zhou, Hang Huang, Rui Zhao, Rui Zhou and Qingguo Zhou
• Abstract summary: In the field of object detection, the task of object localization is typically accomplished through a dedicated that emphasizes bounding box regression. This traditionally predicts the object's position by regressing the box's center position and scaling factors. In this paper, we address the shortcomings of previous methods through theoretical analysis and experimental verification. Our approach enhances the accuracy of bounding box localization by refining the box edges based on the estimated distribution at the object's boundary.
• Score: 12.247010914825971
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In the field of state-of-the-art object detection, the task of object localization is typically accomplished through a dedicated subnet that emphasizes bounding box regression. This subnet traditionally predicts the object's position by regressing the box's center position and scaling factors. Despite the widespread adoption of this approach, we have observed that the localization results often suffer from defects, leading to unsatisfactory detector performance. In this paper, we address the shortcomings of previous methods through theoretical analysis and experimental verification and present an innovative solution for precise object detection. Instead of solely focusing on the object's center and size, our approach enhances the accuracy of bounding box localization by refining the box edges based on the estimated distribution at the object's boundary. Experimental results demonstrate the potential and generalizability of our proposed method.

Related papers

• DiffuBox: Refining 3D Object Detection with Point Diffusion [74.01759893280774]
  We introduce a novel diffusion-based box refinement approach to ensure robust 3D object detection and localization. We evaluate this approach under various domain adaptation settings, and our results reveal significant improvements across different datasets.
  arXiv  Detail & Related papers  (2024-05-25T03:14:55Z)
• Rigidity-Aware Detection for 6D Object Pose Estimation [60.88857851869196]
  Most recent 6D object pose estimation methods first use object detection to obtain 2D bounding boxes before actually regressing the pose. We propose a rigidity-aware detection method exploiting the fact that, in 6D pose estimation, the target objects are rigid. Key to the success of our approach is a visibility map, which we propose to build using a minimum barrier distance between every pixel in the bounding box and the box boundary.
  arXiv  Detail & Related papers  (2023-03-22T09:02:54Z)
• Confidence-driven Bounding Box Localization for Small Object Detection [30.906712428887147]
  We present Confidence-driven Bounding Box localization (C-BBL) method to rectify the gradients. C-BBL quantizes continuous labels into grids and formulates two-hot ground truth labels. We demonstrate the generalizability of C-BBL to different label systems and effectiveness for high resolution detection.
  arXiv  Detail & Related papers  (2023-03-03T09:19:08Z)
• Uncertainty Calibration and its Application to Object Detection [0.0]
  In this work, we examine the semantic uncertainty (which object type?) as well as the spatial uncertainty. We evaluate if the predicted uncertainties of an object detection model match with the observed error that is achieved on real-world data.
  arXiv  Detail & Related papers  (2023-02-06T08:41:07Z)
• Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection [12.807987076435928]
  This work tackles the unsupervised cross-domain object detection problem. It aims to generalize a pre-trained object detector to a new target domain without labels.
  arXiv  Detail & Related papers  (2021-08-28T09:37:18Z)
• 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)
• Bi-Dimensional Feature Alignment for Cross-Domain Object Detection [71.85594342357815]
  We propose a novel unsupervised cross-domain detection model. It exploits the annotated data in a source domain to train an object detector for a different target domain. The proposed model mitigates the cross-domain representation divergence for object detection.
  arXiv  Detail & Related papers  (2020-11-14T03:03:11Z)
• Dive Deeper Into Box for Object Detection [49.923586776690115]
  We propose a box reorganization method(DDBNet), which can dive deeper into the box for more accurate localization. Experimental results show that our method is effective which leads to state-of-the-art performance for object detection.
  arXiv  Detail & Related papers  (2020-07-15T07:49:05Z)
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation [62.29076080124199]
  This paper proposes a novel coarse-to-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains.
  arXiv  Detail & Related papers  (2020-03-23T13:40:06Z)
• Mixup Regularization for Region Proposal based Object Detectors [0.0]
  We propose to leverage the inherent region mapping structure of anchors to introduce a mixup-driven training regularization for region proposal based object detectors. Our experiments show an enhanced robustness to image alterations along with an ability to decontextualize detections, resulting in an improved generalization power.
  arXiv  Detail & Related papers  (2020-03-04T13:16:45Z)

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.