Papers › Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection

Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection

5 Mar 2022CVPR 2022 1arXiv:2203.02688archive 2025-07-28

Pang Youwei, Zhao Xiaoqi, Xiang Tian-Zhu, Zhang Lihe, Lu Huchuan

The recently proposed camouflaged object detection (COD) attempts to segment objects that are visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from high intrinsic similarity between the camouflaged objects and their background, the objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To deal with these problems, we propose a mixed-scale triplet network, ZoomNet, which mimics the behavior of humans when observing vague images, i.e., zooming in and out. Specifically, our ZoomNet employs the zoom strategy to learn the discriminative mixed-scale semantics by the designed scale integration unit and hierarchical mixed-scale unit, which fully explores imperceptible clues between the candidate objects and background surroundings. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization constraint, uncertainty-aware loss, to promote the model to accurately produce predictions with higher confidence in candidate regions. Without bells and whistles, our proposed highly task-friendly model consistently surpasses the existing 23 state-of-the-art methods on four public datasets. Besides, the superior performance over the recent cutting-edge models on the SOD task also verifies the effectiveness and generality of our model. The code will be available at https://github.com/lartpang/ZoomNet.

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 13 code samples harvested from 1 repository linked to this paper: 12 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 12 ran (8 with no instrument failure; 4 where Syntology's instrument failed). 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lartpang/zoomnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 12 ran (4 instrument-failed) · 1 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

13 samples harvested: 12 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 1 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.

1ran · honoured contract
4ran · our draft was wrong
7ran
1unverified

Licence: 0 of the 13 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 lartpang/zoomnet. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

lartpang/zoomnet official repository 13 samples, 12 ran (4 instrument-failed) · 1 unverified
ASPP in 23 papers methods/zoomnet/zoomnet.py ran MIT (permissive) · baaa14215b7042ce · report fixture: returned ASPP · level recorded 2026-09-22
BasicModelClass methods/zoomnet/zoomnet.py ran MIT (permissive) · 05985573b34cdbec · report fixture: returned BasicModelClass · level recorded 2026-09-22
ConvBNReLU in 16 papers methods/zoomnet/zoomnet.py ran fingerprinted MIT (permissive) · 862d137d282a2bab · report fixture: returned ConvBNReLU · level recorded 2026-09-22
HMU methods/zoomnet/zoomnet.py ran MIT (permissive) · 7643f062b521c4d3 · report fixture: returned HMU · level recorded 2026-09-22
Registry in 34 papers methods/zoomnet/zoomnet.py ran MIT (permissive) · 4a417a63c358c5ab · report fixture: returned Registry · level recorded 2026-09-22
SIU methods/zoomnet/zoomnet.py ran MIT (permissive) · aec31add8468eb86 · report fixture: returned SIU · level recorded 2026-09-22
TransLayer in 8 papers methods/zoomnet/zoomnet.py ran MIT (permissive) · 0fa380f44af066ff · report fixture: returned TransLayer · level recorded 2026-09-22
_get_act_fn methods/zoomnet/zoomnet.py ran · our draft was wrong MIT (permissive) · 22f8cb77f8cc8af2 · report fixture: signature act_name:str/0/str, inplace:bool/0/bool · returned ReLU · level recorded 2026-09-22
cal_ual methods/zoomnet/zoomnet.py ran · our draft was wrong fingerprinted MIT (permissive) · 1c4040dd702dbed1 · report fixture: signature seg_logits:Tensor/2/float, seg_gts:Tensor/2/float · returned Tensor · level recorded 2026-09-22
formatter_for_dict methods/zoomnet/zoomnet.py ran · our draft was wrong MIT (permissive) · a1699c744bd715fd · report fixture: signature info_dict:dict/0/?, headers:list/1/str, name_length:int/0/int, obj_str_length:int/0/int · returned str · level recorded 2026-09-22
get_coef in 8 papers methods/zoomnet/zoomnet.py ran · honoured contract MIT (permissive) · 1ed4fe7e2e6020fa · report fixture: signature iter_percentage:float/0/float, method:str/0/str · returned float · level recorded 2026-09-22
item2str methods/zoomnet/zoomnet.py ran · our draft was wrong fingerprinted MIT (permissive) · ce165bae8262bf4c · report fixture: signature string:str/0/str, max_length:int/0/int, padding_char:str/0/str, mode:str/0/str · returned str · level recorded 2026-09-22
ZoomNet methods/zoomnet/zoomnet.py unverified MIT (permissive) · 6e01acf2e56ffb95 · 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 Zoom-Net (graph method: Zoom-Net). 13 bricks; individually on a fixture: 12 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. ZoomNet entry · level 0 · unverified · 6e01acf2e56ffb95
  2. BasicModelClass helper · level 1 · ran · 05985573b34cdbec
  3. ConvBNReLU helper · level 1 · ran · 862d137d282a2bab
  4. HMU model · level 1 · ran · 7643f062b521c4d3
  5. SIU model · level 1 · ran · aec31add8468eb86
  6. TransLayer model · level 1 · ran · 0fa380f44af066ff
  7. cal_ual loss · level 1 · ran · our draft was wrong · 1c4040dd702dbed1
  8. get_coef helper · level 1 · ran · honoured contract · 1ed4fe7e2e6020fa
  9. _get_act_fn helper · level 1 · ran · our draft was wrong · 22f8cb77f8cc8af2
  10. ASPP model · level 1 · ran · baaa14215b7042ce
  11. Registry helper · level 1 · ran · 4a417a63c358c5ab
  12. formatter_for_dict helper · level 1 · ran · our draft was wrong · a1699c744bd715fd
  13. item2str helper · level 1 · ran · our draft was wrong · ce165bae8262bf4c

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="2203.02688") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Camouflaged Object SegmentationImage SegmentationObject Detectionobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camouflaged Object Segmentation PCOD_1200 ZoomNet S-Measure 0.897 #4 of 16 Archive leaderboard report
Image Segmentation MAS3K ZoomNet E-measure 0.898 #4 of 4 Archive leaderboard report
Image Segmentation MAS3K ZoomNet MAE 0.032 #4 of 4 Archive leaderboard report
Image Segmentation MAS3K ZoomNet S-measure 0.862 #4 of 4 Archive leaderboard report
Image Segmentation MAS3K ZoomNet mIoU 0.736 #4 of 4 Archive leaderboard report
Image Segmentation RMAS ZoomNet E-measure 0.915 #4 of 4 Archive leaderboard report
Image Segmentation RMAS ZoomNet MAE 0.022 #4 of 4 Archive leaderboard report
Image Segmentation RMAS ZoomNet S-measure 0.855 #4 of 4 Archive leaderboard report
Image Segmentation RMAS ZoomNet mIoU 0.728 #4 of 4 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

ZoomNet

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