Yiting Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yiting Cheng has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Wenqiang Zhang
Fudan University, Shanghai, China
3 shared publications - Dingkang Yang
Fudan University, Shanghai, China
1 shared publication - Dong Chen
Microsoft Research Asia, Beijing, China
1 shared publication - Fangyun Wei
School of Computer Science, University of Sydney, Darlington, NSW, Australia
1 shared publication - Haozhe Xing
Fudan University, Shanghai, China
1 shared publication Jianmin Bao
Microsoft Research Asia, Beijing, China
1 shared publication
Latest Publications
- 30 April 2026
- Published by Elsevier in Neural Networks
- Vol. 202, 109020
Delving into the adversarial robustness of semantic segmentation with decision-based black-box attacks
- 30 April 2026
- Published by Elsevier in Neural Networks
- Vol. 202, 109020
Delving into the adversarial robustness of semantic segmentation with decision-based black-box attacks
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5532-5541
Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context
Unsupervised salient object detection aims to detect salient objects without using supervision signals eliminating the tedious task of manually labeling salient objects. To improve training efficiency, end-to-end methods for USOD have been proposed as a promising alternative. However, current solutions rely heavily on noisy handcraft labels and fail to mine rich semantic information from deep features. In this paper, we propose a self-supervised end-to-end salient object detection framework via top-down context. Specifically, motivated by contrastive learning, we exploit the self-localization from the deepest feature to construct the location maps which are then leveraged to learn the most instructive segmentation guidance. Further considering the lack of detailed information in deepest features, we exploit the detail-boosting refiner module to enrich the location labels with details. Moreover, we observe that due to lack of supervision, current unsupervised saliency models tend to detect non-salient objects that are salient in some other samples of corresponding scenarios. To address this widespread issue, we design a novel Unsupervised Non-Salient Suppression (UNSS) method developing the ability to ignore non-salient objects. Extensive experiments on benchmark datasets demonstrate that our method achieves leading performance among the recent end-to-end methods and most of the multi-stage solutions. The code is available.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5532-5541
Open AccessTowards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context
Unsupervised salient object detection aims to detect salient objects without using supervision signals eliminating the tedious task of manually labeling salient objects. To improve training efficiency, end-to-end methods for USOD have been proposed as a promising alternative. However, current solutions rely heavily on noisy handcraft labels and fail to mine rich semantic information from deep features. In this paper, we propose a self-supervised end-to-end salient object detection framework via top-down context. Specifically, motivated by contrastive learning, we exploit the self-localization from the deepest feature to construct the location maps which are then leveraged to learn the most instructive segmentation guidance. Further considering the lack of detailed information in deepest features, we exploit the detail-boosting refiner module to enrich the location labels with details. Moreover, we observe that due to lack of supervision, current unsupervised saliency models tend to detect non-salient objects that are salient in some other samples of corresponding scenarios. To address this widespread issue, we design a novel Unsupervised Non-Salient Suppression (UNSS) method developing the ability to ignore non-salient objects. Extensive experiments on benchmark datasets demonstrate that our method achieves leading performance among the recent end-to-end methods and most of the multi-stage solutions. The code is available.
- 23 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 9339-9356
ADPL: Adaptive Dual Path Learning for Domain Adaptation of Semantic Segmentation
To alleviate the need for large-scale pixel-wise annotations, domain adaptation for semantic segmentation trains segmentation models on synthetic data (source) with computer-generated annotations, which can be then generalized to segment realistic images (target). Recently, self-supervised learning (SSL) with a combination of image-to-image translation shows great effectiveness in adaptive segmentation. The most common practice is to perform SSL along with image translation to well align a single domain (source or target). However, in this single-domain paradigm, unavoidable visual inconsistency raised by image translation may affect subsequent learning. In addition, pseudo labels generated by a single segmentation model aligned in either the source or target domain may be not accurate enough for SSL. In this paper, based on the observation that domain adaptation frameworks performed in the source and target domain are almost complementary, we propose a novel adaptive dual path learning (ADPL) framework to alleviate visual inconsistency and promote pseudo-labeling by introducing two interactive single-domain adaptation paths aligned in source and target domain respectively. To fully explore the potential of this dual-path design, novel technologies such as dual path image translation (DPIT), dual path adaptive segmentation (DPAS), dual path pseudo label generation (DPPLG) and Adaptive ClassMix are proposed. The inference of ADPL is extremely simple, only one segmentation model in the target domain is employed. Our ADPL outperforms the state-of-the-art methods by large margins on GTA5$\rightarrow$ Cityscapes, SYNTHIA$\rightarrow$ Cityscapes and GTA5$\rightarrow$ BDD100K scenarios. Code and models are available at https://github.com/royee182/DPL .- 23 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 9339-9356
ADPL: Adaptive Dual Path Learning for Domain Adaptation of Semantic Segmentation
To alleviate the need for large-scale pixel-wise annotations, domain adaptation for semantic segmentation trains segmentation models on synthetic data (source) with computer-generated annotations, which can be then generalized to segment realistic images (target). Recently, self-supervised learning (SSL) with a combination of image-to-image translation shows great effectiveness in adaptive segmentation. The most common practice is to perform SSL along with image translation to well align a single domain (source or target). However, in this single-domain paradigm, unavoidable visual inconsistency raised by image translation may affect subsequent learning. In addition, pseudo labels generated by a single segmentation model aligned in either the source or target domain may be not accurate enough for SSL. In this paper, based on the observation that domain adaptation frameworks performed in the source and target domain are almost complementary, we propose a novel adaptive dual path learning (ADPL) framework to alleviate visual inconsistency and promote pseudo-labeling by introducing two interactive single-domain adaptation paths aligned in source and target domain respectively. To fully explore the potential of this dual-path design, novel technologies such as dual path image translation (DPIT), dual path adaptive segmentation (DPAS), dual path pseudo label generation (DPPLG) and Adaptive ClassMix are proposed. The inference of ADPL is extremely simple, only one segmentation model in the target domain is employed. Our ADPL outperforms the state-of-the-art methods by large margins on GTA5$\rightarrow$ Cityscapes, SYNTHIA$\rightarrow$ Cityscapes and GTA5$\rightarrow$ BDD100K scenarios. Code and models are available at https://github.com/royee182/DPL .