Paper Reading AI Learner

Background Noise Reduction of Attention Map for Weakly Supervised Semantic Segmentation

2024-04-04 11:53:37
Izumi Fujimori, Masaki Oono, Masami Shishibori


In weakly-supervised semantic segmentation (WSSS) using only image-level class labels, a problem with CNN-based Class Activation Maps (CAM) is that they tend to activate the most discriminative local regions of objects. On the other hand, methods based on Transformers learn global features but suffer from the issue of background noise contamination. This paper focuses on addressing the issue of background noise in attention weights within the existing WSSS method based on Conformer, known as TransCAM. The proposed method successfully reduces background noise, leading to improved accuracy of pseudo labels. Experimental results demonstrate that our model achieves segmentation performance of 70.5% on the PASCAL VOC 2012 validation data, 71.1% on the test data, and 45.9% on MS COCO 2014 data, outperforming TransCAM in terms of segmentation performance.

Abstract (translated)

在仅使用图像级别类标签的弱监督语义分割(WSSS)中,基于CNN的分类激活图(CAM)的一个问题在于,它们倾向于激活对象中最具有区分性的局部区域。另一方面,基于Transformer的方法可以学习全局特征,但受到背景噪声污染的问题。本文重点关注在基于Conformer的现有WSSS方法中解决背景噪声问题,称为TransCAM。与TransCAM相比,所提出的方法成功减少了背景噪声,从而提高了伪标签的准确性。实验结果表明,我们的模型在PASCAL VOC 2012验证数据上的分割性能为70.5%,在测试数据上的分割性能为71.1%,在MS COCO 2014数据上的分割性能为45.9%,均优于TransCAM。



3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot