Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation
원문 초록
Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to cost-effectiveness. Recently, Vision Transformer (ViT) based methods without class activation map (CAM) have shown greater capability in generating reliable pseudo labels than previous methods using CAM. However, the current ViT-based methods utilize max pooling to select the patch with the highest prediction score to map the patch-level classification to the image-level one, which may affect the quality of pseudo labels due to the inaccurate classification of the patches. In this paper, we introduce a novel ViT-based WSSS method named top-K pooling with patch contrastive learning (TKP-PCL), which employs a top-K pooling layer to alleviate the limitations of previous max pooling selection. A patch contrastive error (PCE) is also proposed to enhance the patch embeddings to further improve the final results. The experimental results show that our approach is very efficient and outperforms other state-of-the-art WSSS methods on the PASCAL VOC 2012 dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation
MSG-SR-Net: A Weakly Supervised Network Integrating Multi-Scale Generation and Super-Pixel Refinement for Building Extraction from High-Resolution Remotely Sensed Imageries
Group-Wise Learning for Weakly Supervised Semantic Segmentation
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation
Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.