Fuming Sun;Peng Ren;Bowen Yin;Fasheng Wang;Haojie Li
{"title":"CATNet: A Cascaded and Aggregated Transformer Network for RGB-D Salient Object Detection","authors":"Fuming Sun;Peng Ren;Bowen Yin;Fasheng Wang;Haojie Li","doi":"10.1109/TMM.2023.3294003","DOIUrl":null,"url":null,"abstract":"Salient object detection (SOD) is an important preprocessing operation for various computer vision tasks. Most of existing RGB-D SOD models employ additive or connected strategies to directly aggregate and decode multi-scale features to predict salient maps. However, due to the large differences between the features of different scales, these aggregation strategies adopted may lead to information loss or redundancy, and few methods explicitly consider how to establish connections between features at different scales in the decoding process, which consequently deteriorates the detection performance of the models. To this end, we propose a cascaded and aggregated Transformer Network (CATNet) which consists of three key modules, i.e., attention feature enhancement module (AFEM), cross-modal fusion module (CMFM) and cascaded correction decoder (CCD). Specifically, the AFEM is designed on the basis of atrous spatial pyramid pooling to obtain multi-scale semantic information and global context information in high-level features through dilated convolution and multi-head self-attention mechanism, enhancing high-level features. The role of the CMFM is to enhance and thereafter fuse the RGB features and depth features, alleviating the problem of poor-quality depth maps. The CCD is composed of two subdecoders in a cascading fashion. It is designed to suppress noise in low-level features and mitigate the differences between features at different scales. Moreover, the CCD uses a feedback mechanism to correct and repair the output of the subdecoder by exploiting supervised features, so that the problem of information loss caused by the upsampling operation during the multi-scale features aggregation process can be mitigated. Extensive experimental results demonstrate that the proposed CATNet achieves superior performance over 14 state-of-the-art RGB-D methods on 7 challenging benchmarks.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":null,"pages":null},"PeriodicalIF":8.4000,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Multimedia","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10179145/","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Salient object detection (SOD) is an important preprocessing operation for various computer vision tasks. Most of existing RGB-D SOD models employ additive or connected strategies to directly aggregate and decode multi-scale features to predict salient maps. However, due to the large differences between the features of different scales, these aggregation strategies adopted may lead to information loss or redundancy, and few methods explicitly consider how to establish connections between features at different scales in the decoding process, which consequently deteriorates the detection performance of the models. To this end, we propose a cascaded and aggregated Transformer Network (CATNet) which consists of three key modules, i.e., attention feature enhancement module (AFEM), cross-modal fusion module (CMFM) and cascaded correction decoder (CCD). Specifically, the AFEM is designed on the basis of atrous spatial pyramid pooling to obtain multi-scale semantic information and global context information in high-level features through dilated convolution and multi-head self-attention mechanism, enhancing high-level features. The role of the CMFM is to enhance and thereafter fuse the RGB features and depth features, alleviating the problem of poor-quality depth maps. The CCD is composed of two subdecoders in a cascading fashion. It is designed to suppress noise in low-level features and mitigate the differences between features at different scales. Moreover, the CCD uses a feedback mechanism to correct and repair the output of the subdecoder by exploiting supervised features, so that the problem of information loss caused by the upsampling operation during the multi-scale features aggregation process can be mitigated. Extensive experimental results demonstrate that the proposed CATNet achieves superior performance over 14 state-of-the-art RGB-D methods on 7 challenging benchmarks.
期刊介绍:
The IEEE Transactions on Multimedia delves into diverse aspects of multimedia technology and applications, covering circuits, networking, signal processing, systems, software, and systems integration. The scope aligns with the Fields of Interest of the sponsors, ensuring a comprehensive exploration of research in multimedia.