VST++ : Efficient and Stronger Visual Saliency Transformer
Document Type
Article
Publication Title
IEEE Transactions on Pattern Analysis and Machine Intelligence
Abstract
While previous CNN-based models have exhibited promising results for salient object detection (SOD), their ability to explore global long-range dependencies is restricted. Our previous work, the Visual Saliency Transformer (VST), addressed this constraint from a transformer-based sequence-to-sequence perspective, to unify RGB and RGB-D SOD. In VST, we developed a multi-task transformer decoder that concurrently predicts saliency and boundary outcomes in a pure transformer architecture. Moreover, we introduced a novel token upsampling method called reverse T2T for predicting a high-resolution saliency map effortlessly within transformer-based structures. Building upon the VST model, we further propose an efficient and stronger VST version in this work, i.e. VST++. To mitigate the computational costs of the VST model, we propose a Select-Integrate Attention (SIA) module, partitioning foreground into fine-grained segments and aggregating background information into a single coarse-grained token. To incorporate 3D depth information with low cost, we design a novel depth position encoding method tailored for depth maps. Furthermore, we introduce a token-supervised prediction loss to provide straightforward guidance for the task-related tokens. We evaluate our VST++ model across various transformer-based backbones on RGB, RGB-D, and RGB-T SOD benchmark datasets. Experimental results show that our model outperforms existing methods while achieving a 25% reduction in computational costs without significant performance compromise. The demonstrated strong ability for generalization, enhanced performance, and heightened efficiency of our VST++ model highlight its potential.
DOI
10.1109/TPAMI.2024.3388153
Publication Date
1-1-2024
Keywords
Computational modeling, Computer architecture, Decoding, Feature extraction, Multi-task learning, Multitasking, RGB-D saliency detection, RGB-T saliency detection, saliency detection, Task analysis, transformer, Transformers
Recommended Citation
N.
Liu
et al.,
"VST
The definitive version is available at https://doi.org/10.1109/TPAMI.2024.3388153