Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation

2024-04-01 · Beomyoung Kim, Donghyun Kim, Sung Ju Hwang

This paper presents a fresh perspective on the role of saliency maps in weakly-supervised semantic segmentation (WSSS) and offers new insights and research directions based on our empirical findings. We conduct comprehensive experiments and observe that the quality of the saliency map is a critical factor in saliency-guided WSSS approaches. Nonetheless, we find that the saliency maps used in previous works are often arbitrarily chosen, despite their significant impact on WSSS. Additionally, we observe that the choice of the threshold, which has received less attention before, is non-trivial in WSSS. To facilitate more meaningful and rigorous research for saliency-guided WSSS, we introduce \texttt{WSSS-BED}, a standardized framework for conducting research under unified conditions. \texttt{WSSS-BED} provides various saliency maps and activation maps for seven WSSS methods, as well as saliency maps from unsupervised salient object detection models.

📄 PDF Abstract BibTeX arXiv:2404.00918

Code (1)

clovaai/wsss-bed 공식 구현 pytorch

Tasks

object-detection Object Detection Salient Object Detection Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation

2019-10-12 · Qi Yao, Xiaojin Gong

Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest. However, its performance is still inferior t…

Segmentation Semantic Segmentation Semi-Supervised Semantic Segmentation Weakly supervised Semantic Segmentation+1

Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing

2016-06-01 · CVPR 2016 6 · Baisheng Lai, Xiaojin Gong

In this paper, we propose a novel method to perform weakly-supervised image parsing based on the dictionary learning framework. To deal with the challenges caused by the label ambiguities, we design a saliency guided wei…

Dictionary Learning Saliency Detection

Saliency Guided End-to-End Learning for Weakly Supervised Object Detection

2017-06-21 · Baisheng Lai, Xiaojin Gong

Weakly supervised object detection (WSOD), which is the problem of learning detectors using only image-level labels, has been attracting more and more interest. However, this problem is quite challenging due to the lack …

object-detection Object Detection Saliency Prediction Weakly Supervised Object Detection

Hierarchical Semantic Contrast for Weakly Supervised Semantic Segmentation

2023-08-01 · Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence 2023 8 · Yuanchen Wu, Xiaoqiang Li, Songmin Dai, Jide Li 외

Weakly supervised semantic segmentation (WSSS) with image-level annotations has achieved great processes through class activation map (CAM). Since vanilla CAMs are hardly served as guidance to bridge the gap between full…

Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation

2019-09-09 · ICCV 2019 10 · Yu Zeng, Yunzhi Zhuge, Huchuan Lu, Lihe Zhang

Existing weakly supervised semantic segmentation (WSSS) methods usually utilize the results of pre-trained saliency detection (SD) models without explicitly modeling the connections between the two tasks, which is not th…

Multi-Task Learning Saliency Detection Segmentation Semantic Segmentation+3