.png){kind=icon}
返回
DECNet: Dense embedding contrast for unsupervised semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106557.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unsupervised semantic segmentation is important for understanding that each pixel belongs to known categories without annotation. Recent studies have demonstrated promising outcomes by employing a vision transformer backbone pre-trained on an image-level dataset in a self-supervised manner. However, those methods always depend on complex architectures or meticulously designed inputs. Naturally, we are attempting to explore the investment with a straightforward approach. To prevent over-complication, we introduce a simple Dense Embedding Contrast network (DECNet) for unsupervised semantic segmentation in this paper. Specifically, we propose a Nearest Neighbor Similarity strategy (NNS) to establish well-defined positive and negative pairs for dense contrastive learning. Meanwhile, we optimize a contrastive objective named OrthoInfoNCE to alleviate the false negative problem inherent in contrastive learning for further enhancing dense representations. Finally, extensive experiments conducted on COCO-Stuff and Cityscapes datasets demonstrate that our approach outperforms state-of-the-art methods.
Keyword:
Unsupervised learning
Contrastive learning
Contrastive objective
Semantic segmentation
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Multi-level Feature Interaction and Efficient Non-Local Information Enhanced Channel Attention for image dehazing.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏
查看更多内容