11 July 2023 in IEEE Transactions on Multimedia
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. The codes are released at https://github.com/ROC-Star/CATNet/ .
7 February 2025 in Neural Networks
27 January 2025 in Knowledge-Based Systems
2 March 2026 in IEEE Transactions on Multimedia
Recently, some studies have introduced depth cues to solve camouflaged object segmentation (COS) tasks and significantly improve segmentation performance. However, current methods still have two limitations: 1) they are confined to first-order or second-order interaction modeling; 2) they neglect the frequency-domain complementary characteristics between RGB and depth modalities. In this work, we propose a Frequency-domain Fusion and High-order Interaction framework, named F $^{2}$ HI, to alleviate the above limitations. Specifically, F $^{2}$ HI consists of two key components: Frequency Domain Interaction Fusion (FDIF) and the High-order Interaction Unit (HOIU). The FDIF decouples the frequency information of RGB and depth modalities into high-frequency and low-frequency components, utilizing the dominant frequency components of one modality to enhance the weaker frequency components of the other modality, thereby achieving complementary enhancement in the frequency domain. Moreover, it employs cross-attention to facilitate global multimodal interaction. The HOIU employs cascaded self-attention to parse cross-region features generated by multi-object camouflage scenarios, thereby achieving high-order feature interaction. Compared with 27 state-of-the-art COS methods, F $^{2}$ HI achieves competitive performance on four mainstream COS benchmarks.
1 January 2026 in IEEE Transactions on Multimedia