Papers › Multi-view Aggregation Network for Dichotomous Image Segmentation

Multi-view Aggregation Network for Dichotomous Image Segmentation

11 Apr 2024CVPR 2024 1arXiv:2404.07445archive 2025-07-28

Qian Yu, Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu

Dichotomous Image Segmentation (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. When designing an effective DIS model, the main challenge is how to balance the semantic dispersion of high-resolution targets in the small receptive field and the loss of high-precision details in the large receptive field. Existing methods rely on tedious multiple encoder-decoder streams and stages to gradually complete the global localization and local refinement. Human visual system captures regions of interest by observing them from multiple views. Inspired by it, we model DIS as a multi-view object perception problem and provide a parsimonious multi-view aggregation network (MVANet), which unifies the feature fusion of the distant view and close-up view into a single stream with one encoder-decoder structure. With the help of the proposed multi-view complementary localization and refinement modules, our approach established long-range, profound visual interactions across multiple views, allowing the features of the detailed close-up view to focus on highly slender structures.Experiments on the popular DIS-5K dataset show that our MVANet significantly outperforms state-of-the-art methods in both accuracy and speed. The source code and datasets will be publicly available at \href{https://github.com/qianyu-dlut/MVANet}{MVANet}.

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="2404.07445")

Code

Syntology Ran 8 of 9 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 2 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

qianyu-dlut/mvanet officialmentioned in papermentioned on GitHubpytorchMIT 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

9 samples harvested; 8 ran; 1 honoured the contract we drafted; 1 has 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
3ran · our draft was wrong
2ran · fixture could not drive it
2ran
1unverified

Licence: 0 of the 9 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 qianyu-dlut/mvanet. “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.

window_partition qianyu-dlut/mvanet/model/SwinTransformer.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report
cv_random_flip qianyu-dlut/mvanet/utils/dataset_strategy_fpn.py official repository ran · fixture could not drive it MIT (permissive) · 41839b27773cccf7 · report
l2_regularisation qianyu-dlut/mvanet/utils/misc.py official repository ran · honoured contract MIT (permissive) · c23b05634625d281 · report
make_cbg qianyu-dlut/mvanet/model/MVANet.py official repository ran MIT (permissive) · 78918720bdb361d4 · report
make_cbr qianyu-dlut/mvanet/model/MVANet.py official repository ran MIT (permissive) · 6ffe5c11970654fa · report
randomCrop qianyu-dlut/mvanet/utils/dataset_strategy_fpn.py official repository ran · our draft was wrong MIT (permissive) · b8fc70f2a16b23cc · report
randomRotation qianyu-dlut/mvanet/utils/dataset_strategy_fpn.py official repository ran · our draft was wrong MIT (permissive) · 8d40bcc4f2cf3edb · report
window_reverse qianyu-dlut/mvanet/model/SwinTransformer.py official repository ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report
get_activation_fn qianyu-dlut/mvanet/model/MVANet.py official repository unverified MIT (permissive) · f2e72d81f39d65cd · report

Tasks

DecoderDichotomous Image SegmentationImage SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dichotomous Image Segmentation DIS-TE1 MVANet E-measure 0.911 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MVANet HCE 104 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MVANet MAE 0.037 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MVANet S-Measure 0.879 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MVANet max F-Measure 0.873 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MVANet weighted F-measure 0.823 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MVANet E-measure 0.944 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MVANet HCE 251 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MVANet MAE 0.030 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MVANet S-Measure 0.915 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MVANet max F-Measure 0.916 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MVANet weighted F-measure 0.874 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MVANet E-measure 0.954 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MVANet HCE 525 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MVANet MAE 0.031 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MVANet S-Measure 0.920 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MVANet max F-Measure 0.929 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MVANet weighted F-measure 0.890 #2 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MVANet E-measure 0.944 #1 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MVANet HCE 2331 #1 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MVANet MAE 0.041 #1 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MVANet S-Measure 0.903 #1 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MVANet max F-Measure 0.912 #1 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MVANet weighted F-measure 0.857 #1 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MVANet E-measure 0.941 #4 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MVANet HCE 893 #4 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MVANet MAE 0.034 #4 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MVANet S-Measure 0.905 #4 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MVANet max F-Measure 0.904 #4 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MVANet weighted F-measure 0.863 #4 of 24 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

Focus

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