VST++: Efficient and Stronger Visual Saliency Transformer

arXiv:2310.11725v2 Announce Type: replace
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 …

abstract arxiv cnn cs.cv dependencies detection explore global object perspective results rgb-d transformer type visual work