Papers › Visual Saliency Transformer

Visual Saliency Transformer

25 Apr 2021ICCV 2021 10arXiv:2104.12099archive 2025-07-28

Nian Liu, Ni Zhang, Kaiyuan Wan, Ling Shao, Junwei Han

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2104.12099")

Code

Syntology Ran 7 of 11 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 6 ran with no contract checked.

By repository: named in the paper: 4 samples from 1 repository, 3 ran; community (archive-listed): 6 samples from 1 repository, 3 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nnizhang/VST mentioned in paperpytorch report
fhshen2022/prunerepaint mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 7 ran; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
6ran
4unverified

Licence: 11 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Attention nnizhang/VST/RGBD_VST/Models/Transformer.py named in the paper ran no licence file found · pointer only · e518414e453d6bd4 · report
MutualAttention nnizhang/VST/RGBD_VST/Models/Transformer.py named in the paper ran no licence file found · pointer only · f19483886b6caa8a · report
MutualSelfBlock nnizhang/VST/RGBD_VST/Models/Transformer.py named in the paper ran no licence file found · pointer only · ad3ceaa863c245d9 · report
TransformerEncoder nnizhang/VST/RGBD_VST/Models/Transformer.py named in the paper unverified no licence file found · pointer only · f9290299b380bb93 · report
T2T_module fhshen2022/prunerepaint/RGB_VST/Models/t2t_vit.py community (archive-listed) ran no licence file found · pointer only · 8f4eb7ec658f7737 · report
Token_performer fhshen2022/prunerepaint/RGB_VST/Models/t2t_vit.py community (archive-listed) ran no licence file found · pointer only · 43b5c1f0c5692aae · report
Token_transformer fhshen2022/prunerepaint/RGB_VST/Models/t2t_vit.py community (archive-listed) ran no licence file found · pointer only · a38451f0ca6db8b5 · report
Attention fhshen2022/prunerepaint/RGB_VST/Models/t2t_vit.py community (archive-listed) unverified no licence file found · pointer only · f6f001c7931d49f2 · report
Block fhshen2022/prunerepaint/RGB_VST/Models/t2t_vit.py community (archive-listed) unverified no licence file found · pointer only · 7c18bbee6c5d2255 · report
T2T_ViT fhshen2022/prunerepaint/RGB_VST/Models/t2t_vit.py community (archive-listed) unverified no licence file found · pointer only · e1a7b5ac434bab26 · report
get_sinusoid_encoding identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · ced6bc2bfdfe0059 · report

Tasks

Boundary DetectionDecoderObject DetectionRGB-D Salient Object DetectionSaliency DetectionSalient Object DetectionThermal Image Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
RGB-D Salient Object Detection NJUD VST S-Measure 0.922 #1 of 1 Archive leaderboard report
RGB-D Salient Object Detection NLPR VST S-Measure 0.932 #14 of 14 Archive leaderboard report
RGB-D Salient Object Detection SIP VST Average MAE 0.040 #2 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP VST S-Measure 90.4 #2 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP VST max E-Measure 94.4 #2 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP VST max F-Measure 91.5 #2 of 16 Archive leaderboard report
Thermal Image Segmentation RGB-T-Glass-Segmentation VST MAE 0.044 #7 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections