Papers › FocalClick: Towards Practical Interactive Image Segmentation

FocalClick: Towards Practical Interactive Image Segmentation

6 Apr 2022CVPR 2022 1arXiv:2204.02574archive 2025-07-28

Xi Chen, Zhiyan Zhao, Yilei Zhang, Manni Duan, Donglian Qi, Hengshuang Zhao

Interactive segmentation allows users to extract target masks by making positive/negative clicks. Although explored by many previous works, there is still a gap between academic approaches and industrial needs: first, existing models are not efficient enough to work on low power devices; second, they perform poorly when used to refine preexisting masks as they could not avoid destroying the correct part. FocalClick solves both issues at once by predicting and updating the mask in localized areas. For higher efficiency, we decompose the slow prediction on the entire image into two fast inferences on small crops: a coarse segmentation on the Target Crop, and a local refinement on the Focus Crop. To make the model work with preexisting masks, we formulate a sub-task termed Interactive Mask Correction, and propose Progressive Merge as the solution. Progressive Merge exploits morphological information to decide where to preserve and where to update, enabling users to refine any preexisting mask effectively. FocalClick achieves competitive results against SOTA methods with significantly smaller FLOPs. It also shows significant superiority when making corrections on preexisting masks. Code and data will be released at github.com/XavierCHEN34/ClickSEG

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 21 code samples: 20 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 21: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 14 ran (10 with no instrument failure; 4 where Syntology's instrument failed); 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

XavierCHEN34/ClickSEG officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 14 ran (4 instrument-failed) · 6 unverified 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

21 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
1ran; the contract check could not run
10ran
7unverified

Licence: 1 of the 21 samples is 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 XavierCHEN34/ClickSEG. 1 sample is listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

XavierCHEN34/ClickSEG official repository 20 samples, 14 ran (4 instrument-failed) · 6 unverified
BasicBlockV1b isegm/model/is_hrnet_model.py ran Apache-2.0 (permissive) · 7e0099013f714d0b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
BatchImageNormalize isegm/model/is_hrnet_model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 339f5051599196e6 · report fixture: signature tensor:Tensor/4/float · returned Tensor · level recorded 2026-09-22
BottleneckV1b isegm/model/is_hrnet_model.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · d040bbf8b42c1853 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ConvModule in 8 papers isegm/model/is_hrnet_model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 36ecf3e15546035e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LRMult isegm/model/is_hrnet_model.py ran Apache-2.0 (permissive) · 2028862f40603cc7 · report fixture: signature m:callable/0/? · returned NoneType · level recorded 2026-09-24
ObjectAttentionBlock2D isegm/model/is_hrnet_model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · e0f1a4750642d91b · report fixture: signature x:Tensor/4/float, proxy:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ScaleLayer in 5 papers isegm/model/is_hrnet_model.py ran fingerprinted Apache-2.0 (permissive) · 7c22256846b5a788 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
SpatialGather_Module isegm/model/is_hrnet_model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · fc329aee6357b551 · report fixture: signature feats:Tensor/4/float, probs:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SpatialOCR_Module isegm/model/is_hrnet_model.py ran fingerprinted Apache-2.0 (permissive) · 7936d6a591621025 · report fixture: signature feats:Tensor/4/float, proxy_feats:Tensor/4/float · returned Tensor · level recorded 2026-09-24
XConvBnRelu isegm/model/is_hrnet_model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 44f751550a0af371 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_classname isegm/model/is_hrnet_model.py ran · our draft was wrong Apache-2.0 (permissive) · 532fac016c7c896a · report fixture: signature cls:callable/0/? · returned str · level recorded 2026-09-22
get_default_params in 12 papers isegm/model/is_hrnet_model.py ran · our draft was wrong Apache-2.0 (permissive) · 93ae2e1088f964ad · report fixture: signature some_class:callable/0/? · returned dict · level recorded 2026-09-22
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
isegm/model/is_hrnet_model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 55bc02c6846634c4 · report fixture: signature input:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, mode:str/0/str, align_corners:NoneType/0/? · returned Tensor · level recorded 2026-09-22
serialize in 19 papers isegm/model/is_hrnet_model.py ran · our draft was wrong Apache-2.0 (permissive) · a4cd31544f3ea2b5 · report fixture: signature init:callable/0/? · returned function · level recorded 2026-09-22
DistMaps isegm/model/is_hrnet_model.py unverified Apache-2.0 (permissive) · 524aba093ebca5b5 · report
HRNetModel isegm/model/is_hrnet_model.py unverified Apache-2.0 (permissive) · 5eac58acde5ed053 · report
HighResolutionModule in 10 papers isegm/model/is_hrnet_model.py unverified Apache-2.0 (permissive) · c3e49580d712bb6f · report
HighResolutionNet in 6 papers isegm/model/is_hrnet_model.py unverified Apache-2.0 (permissive) · 79f5c9927f655378 · report
ISModel isegm/model/is_hrnet_model.py unverified Apache-2.0 (permissive) · 0467c4cb28e2a662 · report
RefineLayer isegm/model/is_hrnet_model.py unverified Apache-2.0 (permissive) · f8c13074d5a56e32 · report
Repository not located 1 sample, 0 ran · 1 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
split_points_by_order in 5 papers repository not located unverified licence of this copy not recorded · 8bb23b71c17a0a25 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for FocalClick (graph method: FocalClick). 21 bricks; individually on a fixture: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. HRNetModel entry · level 0 · unverified · 5eac58acde5ed053
  2. DistMaps helper · level 0 · unverified · 524aba093ebca5b5
  3. HighResolutionNet helper · level 0 · unverified · 79f5c9927f655378
  4. ISModel helper · level 0 · unverified · 0467c4cb28e2a662
  5. LRMult helper · level 1 · ran · 2028862f40603cc7
  6. RefineLayer model · level 0 · unverified · f8c13074d5a56e32
  7. serialize helper · level 1 · ran · our draft was wrong · a4cd31544f3ea2b5
  8. BasicBlockV1b helper · level 1 · ran · 7e0099013f714d0b
  9. BottleneckV1b helper · level 1 · ran · d040bbf8b42c1853
  10. HighResolutionModule helper · level 0 · unverified · c3e49580d712bb6f
  11. SpatialGather_Module helper · level 1 · ran · fc329aee6357b551
  12. SpatialOCR_Module helper · level 1 · ran · 7936d6a591621025
  13. BatchImageNormalize helper · level 1 · ran · 339f5051599196e6
  14. ScaleLayer helper · level 1 · ran · 7c22256846b5a788
  15. split_points_by_order helper · level 0 · unverified · 8bb23b71c17a0a25
  16. ConvModule model · level 1 · ran · 36ecf3e15546035e
  17. XConvBnRelu model · level 1 · ran · 44f751550a0af371
  18. resize helper · level 1 · ran; the contract check could not run (RAISES) · 55bc02c6846634c4
  19. get_classname helper · level 1 · ran · our draft was wrong · 532fac016c7c896a
  20. get_default_params helper · level 1 · ran · our draft was wrong · 93ae2e1088f964ad
  21. ObjectAttentionBlock2D helper · level 1 · ran · e0f1a4750642d91b

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2204.02574") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image SegmentationInteractive SegmentationSegmentationSemantic Segmentation

Datasets

Introduced by this paper, per the archive.

DAVIS-585

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Interactive Segmentation Berkeley FocalClick-B3-S2 NoC@90 1.48 #2 of 14 Archive leaderboard report
Interactive Segmentation DAVIS FocalClick-B3-S2 NoC@85 2.92 #2 of 15 Archive leaderboard report
Interactive Segmentation DAVIS FocalClick-B3-S2 NoC@90 4.52 #2 of 15 Archive leaderboard report
Interactive Segmentation DAVIS-585 FocalClick-B3-S2 NoC@90 2.76 #2 of 2 Archive leaderboard report
Interactive Segmentation SBD FocalClick NoC@85 3.53 #7 of 14 Archive leaderboard report
Interactive Segmentation SBD FocalClick NoC@90 5.59 #7 of 14 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