Papers › Explicit Visual Prompting for Low-Level Structure Segmentations

Explicit Visual Prompting for Low-Level Structure Segmentations

20 Mar 2023CVPR 2023 1arXiv:2303.10883archive 2025-07-28

Weihuang Liu, Xi Shen, Chi-Man Pun, Xiaodong Cun

We consider the generic problem of detecting low-level structures in images, which includes segmenting the manipulated parts, identifying out-of-focus pixels, separating shadow regions, and detecting concealed objects. Whereas each such topic has been typically addressed with a domain-specific solution, we show that a unified approach performs well across all of them. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and the input's high-frequency components. The proposed EVP significantly outperforms other parameter-efficient tuning protocols under the same amount of tunable parameters (5.7% extra trainable parameters of each task). EVP also achieves state-of-the-art performances on diverse low-level structure segmentation tasks compared to task-specific solutions. Our code is available at: https://github.com/NiFangBaAGe/Explicit-Visual-Prompt.

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="2303.10883")

Code

Syntology Ran 4 of 4 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nifangbaage/explicit-visual-prompt officialmentioned in papermentioned 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

4 samples harvested; 4 ran; 0 honoured the contract we drafted; 0 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.

4ran

Licence: 0 of the 4 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 nifangbaage/explicit-visual-prompt. “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.

GaussianFilter nifangbaage/explicit-visual-prompt/models/mmseg/models/backbones/mix_transformer_evp.py official repository ran BSD-3-Clause (permissive) · f8888ddf26984020 · report
OverlapPatchEmbed nifangbaage/explicit-visual-prompt/models/mmseg/models/backbones/mix_transformer_evp.py official repository ran fingerprinted BSD-3-Clause (permissive) · fd382d2bcab3fdde · report
PromptGenerator nifangbaage/explicit-visual-prompt/models/mmseg/models/backbones/mix_transformer_evp.py official repository ran BSD-3-Clause (permissive) · 1260af12c9528947 · report
SRMFilter nifangbaage/explicit-visual-prompt/models/mmseg/models/backbones/mix_transformer_evp.py official repository ran fingerprinted BSD-3-Clause (permissive) · 899db2d7c10da202 · report

Tasks

Camouflaged Object SegmentationDefocus Blur DetectionForeground SegmentationImage Manipulation DetectionSalient Object DetectionShadow DetectionVisual Prompting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camouflaged Object Segmentation CAMO EVPv1 MAE 0.059 #6 of 14 Archive leaderboard report
Camouflaged Object Segmentation CAMO EVPv1 S-Measure 0.846 #6 of 14 Archive leaderboard report
Camouflaged Object Segmentation CAMO EVPv1 Weighted F-Measure 0.777 #6 of 14 Archive leaderboard report
Camouflaged Object Segmentation COD EVPv1 MAE 0.029 #7 of 12 Archive leaderboard report
Camouflaged Object Segmentation COD EVPv1 S-Measure 0.843 #7 of 12 Archive leaderboard report
Camouflaged Object Segmentation COD EVPv1 Weighted F-Measure 0.742 #7 of 12 Archive leaderboard report
Salient Object Detection ECSSD EVPv1 E-measure 0.957 #4 of 10 Archive leaderboard report
Salient Object Detection ECSSD EVPv1 MAE 0.027 #4 of 10 Archive leaderboard report
Salient Object Detection ECSSD EVPv1 S-measure 0.935 #4 of 10 Archive leaderboard report
Salient Object Detection ECSSD EVPv1 max_F1 0.960 #4 of 10 Archive leaderboard report
Salient Object Detection HKU-IS EVPv1 E-measure 0.961 #4 of 9 Archive leaderboard report
Salient Object Detection HKU-IS EVPv1 MAE 0.024 #4 of 9 Archive leaderboard report
Salient Object Detection HKU-IS EVPv1 S-measure 0.931 #4 of 9 Archive leaderboard report
Salient Object Detection HKU-IS EVPv1 max_F1 0.952 #4 of 9 Archive leaderboard report
Salient Object Detection PASCAL-S EVPv1 E-measure 0.917 #4 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S EVPv1 MAE 0.054 #4 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S EVPv1 S-measure 0.878 #4 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S EVPv1 max_F1 0.872 #4 of 10 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.

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