AccLoc: Anchor-Free and two-stage detector for accurate object localization. (June 2022)
- Record Type:
- Journal Article
- Title:
- AccLoc: Anchor-Free and two-stage detector for accurate object localization. (June 2022)
- Main Title:
- AccLoc: Anchor-Free and two-stage detector for accurate object localization
- Authors:
- Piao, Zhengquan
Wang, Junbo
Tang, Linbo
Zhao, Baojun
Wang, Wenzheng - Abstract:
- Highlights: We proposed an anchor-free, NMS-free and two-stage object detection framework for accurate localization. Adaptive proposal jitter strategy contributes to learning the mappings between the input regional features and the desired output offsets. Proposal fine-tuning strategy encourages the networks to cover various and helpful features for the subsequent bounding box regression process. Extensive experiments on COCO, KITTI, and BDD100K were conducted to demonstrate the effectiveness of our proposed approach. Abstract: Current anchor-free object detectors have obtained detection performances comparable to those of anchor-based object detectors while avoiding the weaknesses of anchor designs. However, two challenges limit the localization performance. First, such anchor-free detectors have one stage that predicts the classification and localization results directly. A large regression space reduces the localization performance of such methods. Second, most of the existing detectors extract features which are ineffective for accurate localization. In this paper, for the first challenge, we propose two-stage networks to predict regression results stage by stage, thereby reducing the scope of the prediction space. For the second challenge, we design two novel modules with the aim of extracting effective features for accurate localization. Experimental results validate that each module in our approach is effective and validate that our approach has better objectHighlights: We proposed an anchor-free, NMS-free and two-stage object detection framework for accurate localization. Adaptive proposal jitter strategy contributes to learning the mappings between the input regional features and the desired output offsets. Proposal fine-tuning strategy encourages the networks to cover various and helpful features for the subsequent bounding box regression process. Extensive experiments on COCO, KITTI, and BDD100K were conducted to demonstrate the effectiveness of our proposed approach. Abstract: Current anchor-free object detectors have obtained detection performances comparable to those of anchor-based object detectors while avoiding the weaknesses of anchor designs. However, two challenges limit the localization performance. First, such anchor-free detectors have one stage that predicts the classification and localization results directly. A large regression space reduces the localization performance of such methods. Second, most of the existing detectors extract features which are ineffective for accurate localization. In this paper, for the first challenge, we propose two-stage networks to predict regression results stage by stage, thereby reducing the scope of the prediction space. For the second challenge, we design two novel modules with the aim of extracting effective features for accurate localization. Experimental results validate that each module in our approach is effective and validate that our approach has better object localization performance than previous related and advanced methods. … (more)
- Is Part Of:
- Pattern recognition. Volume 126(2022)
- Journal:
- Pattern recognition
- Issue:
- Volume 126(2022)
- Issue Display:
- Volume 126, Issue 2022 (2022)
- Year:
- 2022
- Volume:
- 126
- Issue:
- 2022
- Issue Sort Value:
- 2022-0126-2022-0000
- Page Start:
- Page End:
- Publication Date:
- 2022-06
- Subjects:
- Object detection -- Accurate localization -- Anchor-free -- NMS-free -- Two-stage
Pattern perception -- Periodicals
Perception des structures -- Périodiques
Patroonherkenning
006.4 - Journal URLs:
- http://www.sciencedirect.com/science/journal/00313203 ↗
http://www.sciencedirect.com/ ↗ - DOI:
- 10.1016/j.patcog.2022.108523 ↗
- Languages:
- English
- ISSNs:
- 0031-3203
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 22254.xml