Papers › Unified Unsupervised Salient Object Detection via Knowledge Transfer

Unified Unsupervised Salient Object Detection via Knowledge Transfer

23 Apr 2024arXiv:2404.14759archive 2025-07-28

Yao Yuan, Wutao Liu, Pan Gao, Qun Dai, Jie Qin

Recently, unsupervised salient object detection (USOD) has gained increasing attention due to its annotation-free nature. However, current methods mainly focus on specific tasks such as RGB and RGB-D, neglecting the potential for task migration. In this paper, we propose a unified USOD framework for generic USOD tasks. Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network. This mechanism starts with easy samples and progressively moves towards harder ones, to avoid initial interference caused by hard samples. Afterwards, the obtained saliency cues are utilized to train a saliency detector, and we employ a Self-rectify Pseudo-label Refinement (SPR) mechanism to improve the quality of pseudo-labels. Finally, an adapter-tuning method is devised to transfer the acquired saliency knowledge, leveraging shared knowledge to attain superior transferring performance on the target tasks. Extensive experiments on five representative SOD tasks confirm the effectiveness and feasibility of our proposed method. Code and supplement materials are available at https://github.com/I2-Multimedia-Lab/A2S-v3.

PaperPDFCodeCode 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="2404.14759")

Code

Syntology Ran 12 of 19 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 11 ran with no contract checked.

By repository: official repository: 19 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

I2-Multimedia-Lab/A2S-v3 officialmentioned in papermentioned on GitHubpytorchMIT report
moothes/a2s-v2 mentioned 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

19 samples harvested; 12 ran; 1 honoured the contract we drafted; 7 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.

1ran · honoured contract
11ran
7unverified

Licence: 0 of the 19 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 I2-Multimedia-Lab/A2S-v3. “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.

CSDloss I2-Multimedia-Lab/A2S-v3/methods/a2s/loss.py official repository ran MIT (permissive) · 07130369e46642a6 · report
base_config I2-Multimedia-Lab/A2S-v3/base/config.py official repository ran MIT (permissive) · ea87b79487497f0f · report
foreground_sign I2-Multimedia-Lab/A2S-v3/methods/a2s/model.py official repository ran fingerprinted MIT (permissive) · cd3f12ad7fd26fce · report
gaussian I2-Multimedia-Lab/A2S-v3/base/loss.py official repository ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report
get_color_list I2-Multimedia-Lab/A2S-v3/data.py official repository ran MIT (permissive) · 47063acb41bffeb6 · report
get_contour I2-Multimedia-Lab/A2S-v3/methods/a2s/loss.py official repository ran fingerprinted MIT (permissive) · e54ad97c27717901 · report
get_rgbd_list I2-Multimedia-Lab/A2S-v3/data.py official repository ran MIT (permissive) · be6334a923c823d3 · report
img_process I2-Multimedia-Lab/A2S-v3/deploy.py official repository ran MIT (permissive) · 48286c49de656a85 · report
normalize I2-Multimedia-Lab/A2S-v3/methods/a2s/model.py official repository ran fingerprinted MIT (permissive) · f1558b293dc0748d · report
normalize I2-Multimedia-Lab/A2S-v3/methods/a2s/saver.py official repository ran fingerprinted MIT (permissive) · 8c9c9229f9687aa0 · report
normalize_pil I2-Multimedia-Lab/A2S-v3/metric.py official repository ran fingerprinted MIT (permissive) · 83d75cc932e35ecd · report
transform I2-Multimedia-Lab/A2S-v3/util.py official repository ran MIT (permissive) · cf264bdd8a060979 · report
BTMLoss I2-Multimedia-Lab/A2S-v3/methods/a2s/loss.py official repository unverified MIT (permissive) · a8b17756540c7c84 · report
Network I2-Multimedia-Lab/A2S-v3/base/model.py official repository unverified MIT (permissive) · 7446e05a85f8aff7 · report
OLR I2-Multimedia-Lab/A2S-v3/data.py official repository unverified MIT (permissive) · 8722be88e6037ef1 · report
SSIM I2-Multimedia-Lab/A2S-v3/base/loss.py official repository unverified MIT (permissive) · 6ebeaf436b45f7d3 · report
create_window I2-Multimedia-Lab/A2S-v3/base/loss.py official repository unverified MIT (permissive) · ac058a4e4f750ebf · report
de_transform I2-Multimedia-Lab/A2S-v3/util.py official repository unverified MIT (permissive) · a27ff48e5be0373c · report
tran_param I2-Multimedia-Lab/A2S-v3/util.py official repository unverified MIT (permissive) · e168235caf726f44 · report

Tasks

ObjectObject DetectionPseudo LabelSalient Object DetectionTransfer Learningobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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