# Visual Saliency Transformer

arXiv: https://arxiv.org/abs/2104.12099 · HTML: https://mlsanity.com/paper/2104.12099/

## Key facts

- Cited by 175 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 93 references that are in the map.
- First posted on arXiv 25 Apr 2021.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [TransTrack: Multiple Object Tracking with Transformer](https://mlsanity.com/paper/2012.15460/) (2020)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [EGNet:Edge Guidance Network for Salient Object Detection](https://mlsanity.com/paper/1908.08297/) (2019)
- [Cascaded Partial Decoder for Fast and Accurate Salient Object Detection](https://mlsanity.com/paper/1904.08739/) (2019)
- [A Simple Pooling-Based Design for Real-Time Salient Object Detection](https://mlsanity.com/paper/1904.09569/) (2019)
- [Multi-scale Interactive Network for Salient Object Detection](https://mlsanity.com/paper/2007.09062/) (2020)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks](https://mlsanity.com/paper/1907.06781/) (2019)

## Built on by (most cited first, 30 of 175)

- [Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.02688/) (2022)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks](https://mlsanity.com/paper/2406.08394/) (2024)
- [Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications](https://mlsanity.com/paper/2304.05750/) (2023)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection](https://mlsanity.com/paper/2304.04709/) (2023)
- [Interpretable Image Classification with Differentiable Prototypes Assignment](https://mlsanity.com/paper/2112.02902/) (2021)
- [Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers](https://mlsanity.com/paper/2303.14816/) (2023)
- [ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection](https://mlsanity.com/paper/2308.07504/) (2023)
- [Specificity-preserving RGB-D Saliency Detection](https://mlsanity.com/paper/2108.08162/) (2021)
- [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022)
- [DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation](https://mlsanity.com/paper/2309.09668/) (2023)
- [SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection](https://mlsanity.com/paper/2204.05585/) (2022)
- [CamoFormer: Masked Separable Attention for Camouflaged Object Detection](https://mlsanity.com/paper/2212.06570/) (2022)
- [VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning](https://mlsanity.com/paper/2311.15011/) (2023)
- [Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction](https://mlsanity.com/paper/2112.13528/) (2021)
- [Learning Non-target Knowledge for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2205.04903/) (2022)
- [Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks](https://mlsanity.com/paper/2210.03265/) (2022)
- [In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation](https://mlsanity.com/paper/2208.04464/) (2022)
- [Advances in Deep Concealed Scene Understanding](https://mlsanity.com/paper/2304.11234/) (2023)
- [Frequency-Spatial Entanglement Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2409.01686/) (2024)
- [TranSalNet: Towards perceptually relevant visual saliency prediction](https://mlsanity.com/paper/2110.03593/) (2021)
- [GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer](https://mlsanity.com/paper/2406.01210/) (2024)
- [SAMAug: Point Prompt Augmentation for Segment Anything Model](https://mlsanity.com/paper/2307.01187/) (2023)
- [Revisiting Image Pyramid Structure for High Resolution Salient Object Detection](https://mlsanity.com/paper/2209.09475/) (2022)
- [HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness](https://mlsanity.com/paper/2301.07405/) (2023)
- [Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection](https://mlsanity.com/paper/2408.04326/) (2024)
- [VST++: Efficient and Stronger Visual Saliency Transformer](https://mlsanity.com/paper/2310.11725/) (2023)
- [RUN: Reversible Unfolding Network for Concealed Object Segmentation](https://mlsanity.com/paper/2501.18783/) (2025)
- [HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection](https://mlsanity.com/paper/2301.03036/) (2023)

## Abstract (arXiv)

Existing state-of-the-art saliency detection methods heavily rely on CNN-based architectures. Alternatively, we rethink this task from a convolution-free sequence-to-sequence perspective and predict saliency by modeling long-range dependencies, which can not be achieved by convolution. Specifically, we develop a novel unified model based on a pure transformer, namely, Visual Saliency Transformer (VST), for both RGB and RGB-D salient object detection (SOD). It takes image patches as inputs and leverages the transformer to propagate global contexts among image patches. Unlike conventional architectures used in Vision Transformer (ViT), we leverage multi-level token fusion and propose a new token upsampling method under the transformer framework to get high-resolution detection results. We also develop a token-based multi-task decoder to simultaneously perform saliency and boundary detection by introducing task-related tokens and a novel patch-task-attention mechanism. Experimental results show that our model outperforms existing methods on both RGB and RGB-D SOD benchmark datasets. Most importantly, our whole framework not only provides a new perspective for the SOD field but also shows a new paradigm for transformer-based dense prediction models. Code is available at https://github.com/nnizhang/VST.