Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909156718411776 |
|---|---|
| author | Kim, Beomyoung Kim, Donghyun Hwang, Sung Ju |
| author_facet | Kim, Beomyoung Kim, Donghyun Hwang, Sung Ju |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00918 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation Kim, Beomyoung Kim, Donghyun Hwang, Sung Ju Computer Vision and Pattern Recognition 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. |
| title | Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.00918 |