DIS-VD Benchmark (Dichotomous Image Segmentation)

24 rows 24 with code listed 6 metrics Dataset page

Currently, existing image segmentation tasks mainly focus on segmenting objects with specific characteristics, e.g., salient, camouflaged, meticulous, or specific categories. Most of them have the same input/output formats, and barely use exclusive mechanisms designed for segmenting targets in their models, which means almost all tasks are dataset-dependent. Thus, it is very promising to formulate a category-agnostic DIS task for accurately segmenting objects with different structure complexities, regardless of their characteristics. Compared with semantic segmentation, the proposed DIS task usually focuses on images with single or a few targets, from which getting richer accurate details of each target is more feasible.

The archive carries no text for this table; the description above is the archive's text for the task Dichotomous Image Segmentation. archive 2025-07-28

Over time archive 2025-07-28

Metric Extra training data

The chart needs JavaScript; the table below carries every value.

Direction inferred from the metric name, not from the archive: MAE (lower is better). Not inferred (points only, no best-so-far line): max F-Measure, weighted F-measure, S-Measure, E-measure, HCE. Points are placed at the row's paper date; 24 of 24 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

									Paper	Code		Ran Syntology	Report
1	BEN_Base	0.923	0.871	0.031	0.916	0.935		✓	Paper	Code	2025	linked, not harvested	report
2	BEN_Base+Refiner	0.919	0.896	0.027	0.917	0.958		✓	Paper	Code	2025	linked, not harvested	report
3	PDFNet	0.913	0.873	0.030	0.916	0.944		–	Paper	Code	2025	linked, not harvested	report
4	MVANet	0.904	0.863	0.034	0.905	0.941	893	–	Paper	Code	2024	8 of 9 ran · 1 unverified	report
5	BiRefNet	0.889	0.853	0.038	0.898	0.928	1006	–	Paper	Code	2024	13 of 14 ran · 1 unverified	report
6	InSPyReNet (HR scale)	0.889			0.900		904	–	Paper	Code	2022	10 of 11 ran · 1 unverified	report
7	InSPyReNet	0.876	0.826	0.043	0.887	0.921	905	–	Paper	Code	2022	10 of 11 ran · 1 unverified	report
8	IS-Net	0.791	0.717	0.074	0.813	0.856	1116	–	Paper	Code	2022	9 of 10 ran · 1 unverified	report
9	U2Net	0.748	0.656	0.090	0.781	0.823	1413	–	Paper	Code	2020	17 of 42 ran · 25 unverified	report
10	HySM	0.734	0.640	0.096	0.773	0.814	1324	–	Paper	Code	2020	linked, not harvested	report
11	BASNet	0.731	0.641	0.094	0.768	0.816	1402	–	Paper	Code	2019	linked, not harvested	report
12	HRNet	0.726	0.641	0.095	0.767	0.824	1560	–	Paper	Code	2019	14 of 34 ran · 20 unverified	report
13	MBV3	0.714	0.642	0.092	0.758	0.841	1625	–	Paper	Code	2019	83 of 105 ran · 22 unverified	report
14	ICNet	0.697	0.609	0.102	0.747	0.811	1503	–	Paper	Code	2017	linked, not harvested	report
15	STDC	0.696	0.613	0.103	0.740	0.817	1598	–	Paper	Code	2021	9 of 16 ran · 7 unverified	report
16	UNet	0.692	0.586	0.113	0.745	0.785	1337	–	Paper	Code	2015	518 of 757 ran · 239 unverified	report
17	PFNet	0.691	0.604	0.106	0.740	0.811	1606	–	Paper	Code	2021	4 of 9 ran · 5 unverified	report
18	PSPNet	0.691	0.603	0.102	0.744	0.802	1588	–	Paper	Code	2016	7 of 29 ran · 22 unverified	report
19	F3Net	0.685	0.595	0.107	0.733	0.800	1567	–	Paper	Code	2019	linked, not harvested	report
20	GateNet	0.678	0.574	0.110	0.723	0.783	1493	–	Paper	Code	2020	linked, not harvested	report
21	SINetV2	0.665	0.584	0.110	0.727	0.798	1568	–	Paper	Code	2021	3 of 3 ran · 0 unverified	report
22	BSV1	0.662	0.548	0.116	0.728	0.767	1660	–	Paper	Code	2018	7 of 18 ran · 11 unverified	report
23	DeeplabV3+	0.660	0.568	0.114	0.716	0.796	1520	–	Paper	Code	2017	3 of 7 ran · 4 unverified	report
24	GCPANet	0.648	0.542	0.118	0.718	0.765	1555	–	Paper	Code	2020	5 of 13 ran · 8 unverified	report

All 24 rows shown. 24 link to a paper page on this site; 2 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 16 rows have a graph line, from 15 distinct papers; 16 rows (15 papers) have at least one sample that ran. Counting each paper once: Syntology ran 710 of 1,077 samples; 367 unverified. Separately, 521 of those 1,077 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-25. Per-sample status is on the paper page.

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