Xiaodong Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaodong Zhao has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Junliang Chen
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR, China
4 shared publications - Linlin Shen
Shenzhen University, Shenzhen, China
4 shared publications - Jianfeng Xiang
Microsoft Research Asia
1 shared publication - Jinheng Xie
National University of Singapore
1 shared publication - Kai Ye
Shenzhen University
1 shared publication - Linna Wang
Guizhou Normal University
1 shared publication
Latest Publications
- 28 December 2023
- Published by Springer Nature
- p. 445-457
JLInst: Boundary-Mask Joint Learning for Instance Segmentation
- 28 December 2023
- Published by Springer Nature
- p. 445-457
JLInst: Boundary-Mask Joint Learning for Instance Segmentation
- Open Access
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object regions. In this paper, we propose Contrastive learning for Class-agnostic Activation Map (C$^2$AM) generation only using unlabeled image data, without the involvement of image-level supervision. The core idea comes from the observation that i) semantic information of foreground objects usually differs from their backgrounds; ii) foreground objects with similar appearance or background with similar color/texture have similar representations in the feature space. We form the positive and negative pairs based on the above relations and force the network to disentangle foreground and background with a class-agnostic activation map using a novel contrastive loss. As the network is guided to discriminate cross-image foreground-background, the class-agnostic activation maps learned by our approach generate more complete object regions. We successfully extracted from C$^2$AM class-agnostic object bounding boxes for object localization and background cues to refine CAM generated by classification network for semantic segmentation. Extensive experiments on CUB-200-2011, ImageNet-1K, and PASCAL VOC2012 datasets show that both WSOL and WSSS can benefit from the proposed C$^2$AM.
Open AccessContrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object regions. In this paper, we propose Contrastive learning for Class-agnostic Activation Map (C$^2$AM) generation only using unlabeled image data, without the involvement of image-level supervision. The core idea comes from the observation that i) semantic information of foreground objects usually differs from their backgrounds; ii) foreground objects with similar appearance or background with similar color/texture have similar representations in the feature space. We form the positive and negative pairs based on the above relations and force the network to disentangle foreground and background with a class-agnostic activation map using a novel contrastive loss. As the network is guided to discriminate cross-image foreground-background, the class-agnostic activation maps learned by our approach generate more complete object regions. We successfully extracted from C$^2$AM class-agnostic object bounding boxes for object localization and background cues to refine CAM generated by classification network for semantic segmentation. Extensive experiments on CUB-200-2011, ImageNet-1K, and PASCAL VOC2012 datasets show that both WSOL and WSSS can benefit from the proposed C$^2$AM.
- Open Access
SLAMs: Semantic Learning based Activation Map for Weakly Supervised Semantic Segmentation
Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches mainly relies on image-level classification learning, which has limited representation capacity. In this paper, we propose a novel semantic learning based framework, named SLAMs (Semantic Learning based Activation Map), for WSSS.
Open AccessSLAMs: Semantic Learning based Activation Map for Weakly Supervised Semantic Segmentation
Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches mainly relies on image-level classification learning, which has limited representation capacity. In this paper, we propose a novel semantic learning based framework, named SLAMs (Semantic Learning based Activation Map), for WSSS.
- 30 September 2021
- Published by Springer Nature
- p. 405-417
Multi-scale Attention-Based Feature Pyramid Networks for Object Detection
- 30 September 2021
- Published by Springer Nature
- p. 405-417
Multi-scale Attention-Based Feature Pyramid Networks for Object Detection
- 29 August 2016
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10033, 100330W-100330W-5
Facial expression recognition based on adaptively weighted improved local binary pattern
- 29 August 2016
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10033, 100330W-100330W-5
Facial expression recognition based on adaptively weighted improved local binary pattern