Learning Camouflaged Object Detection from Noisy Pseudo Label
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_ | 1866916329264513024 |
|---|---|
| author | Zhang, Jin Zhang, Ruiheng Shi, Yanjiao Cao, Zhe Liu, Nian Khan, Fahad Shahbaz |
| author_facet | Zhang, Jin Zhang, Ruiheng Shi, Yanjiao Cao, Zhe Liu, Nian Khan, Fahad Shahbaz |
| contents | Existing Camouflaged Object Detection (COD) methods rely heavily on large-scale pixel-annotated training sets, which are both time-consuming and labor-intensive. Although weakly supervised methods offer higher annotation efficiency, their performance is far behind due to the unclear visual demarcations between foreground and background in camouflaged images. In this paper, we explore the potential of using boxes as prompts in camouflaged scenes and introduce the first weakly semi-supervised COD method, aiming for budget-efficient and high-precision camouflaged object segmentation with an extremely limited number of fully labeled images. Critically, learning from such limited set inevitably generates pseudo labels with serious noisy pixels. To address this, we propose a noise correction loss that facilitates the model's learning of correct pixels in the early learning stage, and corrects the error risk gradients dominated by noisy pixels in the memorization stage, ultimately achieving accurate segmentation of camouflaged objects from noisy labels. When using only 20% of fully labeled data, our method shows superior performance over the state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_13157 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Camouflaged Object Detection from Noisy Pseudo Label Zhang, Jin Zhang, Ruiheng Shi, Yanjiao Cao, Zhe Liu, Nian Khan, Fahad Shahbaz Computer Vision and Pattern Recognition Artificial Intelligence Existing Camouflaged Object Detection (COD) methods rely heavily on large-scale pixel-annotated training sets, which are both time-consuming and labor-intensive. Although weakly supervised methods offer higher annotation efficiency, their performance is far behind due to the unclear visual demarcations between foreground and background in camouflaged images. In this paper, we explore the potential of using boxes as prompts in camouflaged scenes and introduce the first weakly semi-supervised COD method, aiming for budget-efficient and high-precision camouflaged object segmentation with an extremely limited number of fully labeled images. Critically, learning from such limited set inevitably generates pseudo labels with serious noisy pixels. To address this, we propose a noise correction loss that facilitates the model's learning of correct pixels in the early learning stage, and corrects the error risk gradients dominated by noisy pixels in the memorization stage, ultimately achieving accurate segmentation of camouflaged objects from noisy labels. When using only 20% of fully labeled data, our method shows superior performance over the state-of-the-art methods. |
| title | Learning Camouflaged Object Detection from Noisy Pseudo Label |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.13157 |