TY - GEN
T1 - IMAGE AUGMENTATION WITH CONTROLLED DIFFUSION FOR WEAKLY-SUPERVISED SEMANTIC SEGMENTATION
AU - Wu, Wangyu
AU - Dai, Tianhong
AU - Huang, Xiaowei
AU - Ma, Fei
AU - Xiao, Jimin
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using available images and their image-level labels. However, the quality of pseudo labels degrades significantly when the size of available dataset is limited. Thus, in this paper, we tackle this problem from a different view by introducing a novel approach called Image Augmentation with Controlled Diffusion (IACD). This framework effectively augments existing labeled datasets by generating diverse images through controlled diffusion, where the available images and image-level labels are served as the controlling information. Moreover, we also propose a high-quality image selection strategy to mitigate the potential noise introduced by the randomness of diffusion models. In the experiments, our proposed IACD approach clearly surpasses existing state-of-the-art methods. This effect is more obvious when the amount of available data is small, demonstrating the effectiveness of our method.
AB - Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using available images and their image-level labels. However, the quality of pseudo labels degrades significantly when the size of available dataset is limited. Thus, in this paper, we tackle this problem from a different view by introducing a novel approach called Image Augmentation with Controlled Diffusion (IACD). This framework effectively augments existing labeled datasets by generating diverse images through controlled diffusion, where the available images and image-level labels are served as the controlling information. Moreover, we also propose a high-quality image selection strategy to mitigate the potential noise introduced by the randomness of diffusion models. In the experiments, our proposed IACD approach clearly surpasses existing state-of-the-art methods. This effect is more obvious when the amount of available data is small, demonstrating the effectiveness of our method.
KW - diffusion model
KW - high-quality image selection
KW - weakly-supervised semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=85195383335&partnerID=8YFLogxK
U2 - 10.1109/ICASSP48485.2024.10447893
DO - 10.1109/ICASSP48485.2024.10447893
M3 - Conference Proceeding
AN - SCOPUS:85195383335
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 6175
EP - 6179
BT - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Y2 - 14 April 2024 through 19 April 2024
ER -