Papers › Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View...

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

28 Apr 2021ICCV 2021 10arXiv:2104.13963archive 2025-07-28

Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Armand Joulin, Nicolas Ballas, Michael Rabbat

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are assigned similar pseudo-labels. The pseudo-labels are generated non-parametrically, by comparing the representations of the image views to those of a set of randomly sampled labeled images. The distance between the view representations and labeled representations is used to provide a weighting over class labels, which we interpret as a soft pseudo-label. By non-parametrically incorporating labeled samples in this way, PAWS extends the distance-metric loss used in self-supervised methods such as BYOL and SwAV to the semi-supervised setting. Despite the simplicity of the approach, PAWS outperforms other semi-supervised methods across architectures, setting a new state-of-the-art for a ResNet-50 on ImageNet trained with either 10% or 1% of the labels, reaching 75.5% and 66.5% top-1 respectively. PAWS requires 4x to 12x less training than the previous best methods.

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="2104.13963")

Code

Syntology Ran 7 of 21 code samples harvested from 4 repositories linked to this paper; 14 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran; community (archive-listed): 19 samples from 3 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/suncet officialmentioned in papermentioned on GitHubpytorch report
facebookresearch/msn mentioned on GitHubpytorch report
sayakpaul/PAWS-TF mentioned on GitHubtfApache-2.0 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; 7 ran; 0 honoured the contract we drafted; 14 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.

2ran · our draft was wrong
1ran · fixture could not drive it
4ran
14unverified

Licence: 3 of the 21 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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.

AllGather facebookresearch/suncet/src/losses.py official repository ran MIT (permissive) · f68fac75925a8996 · report
init_paws_loss facebookresearch/suncet/src/losses.py official repository ran · our draft was wrong MIT (permissive) · e4fcb778fbb424df · report
AllReduce facebookresearch/msn/src/losses.py community (archive-listed) ran licence not identified · pointer only · 95ac5fe2166b117a · report
PAWS beresandras/semisupervised-classification-keras/algorithms.py community (archive-listed) ran MIT (permissive) · 1bb1dee92e0a093b · report
SemisupervisedModel beresandras/semisupervised-classification-keras/algorithms.py community (archive-listed) ran MIT (permissive) · 71e80bb6a7133768 · report
distributed_sinkhorn facebookresearch/msn/src/losses.py community (archive-listed) ran · fixture could not drive it fingerprinted licence not identified · pointer only · 7478f8e64cee8964 · report
init_msn_loss facebookresearch/msn/src/losses.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 8058e8c73e3a9d20 · report
dataset_for_class sayakpaul/PAWS-TF/utils/labeled_loader.py community (archive-listed) unverified Apache-2.0 (permissive) · 9c8af1a1234a70bb · report
float_parameter sayakpaul/PAWS-TF/utils/multicrop_loader.py community (archive-listed) unverified Apache-2.0 (permissive) · 0f0390c1cd8dff66 · report
get_paws_loss sayakpaul/PAWS-TF/utils/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · 6a55065d9c679d3c · report
get_support_ds sayakpaul/PAWS-TF/utils/labeled_loader.py community (archive-listed) unverified Apache-2.0 (permissive) · c1d2ae4c09280e21 · report
layer sayakpaul/PAWS-TF/models/wide_resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · 05d7d78714b9de1b · report
learner sayakpaul/PAWS-TF/models/resnet20.py community (archive-listed) unverified Apache-2.0 (permissive) · 0756356a6dd842aa · report
onehot_encode sayakpaul/PAWS-TF/utils/labeled_loader.py community (archive-listed) unverified Apache-2.0 (permissive) · fe3cc1bc7312b8a0 · report
projection_head sayakpaul/PAWS-TF/models/wide_resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · cd82cca1cbf4ebbc · report
residual_group sayakpaul/PAWS-TF/models/resnet20.py community (archive-listed) unverified Apache-2.0 (permissive) · abadc575eb223999 · report
sample_level sayakpaul/PAWS-TF/utils/multicrop_loader.py community (archive-listed) unverified Apache-2.0 (permissive) · 08ad311e00fe4f97 · report
snn sayakpaul/PAWS-TF/nn_eval.py community (archive-listed) unverified Apache-2.0 (permissive) · 3d22afdeab459a13 · report
solarize sayakpaul/PAWS-TF/utils/multicrop_loader.py community (archive-listed) unverified Apache-2.0 (permissive) · 879172744bfa9ab1 · report
stem sayakpaul/PAWS-TF/models/resnet20.py community (archive-listed) unverified Apache-2.0 (permissive) · 4771975a4479f016 · report
wide_basic sayakpaul/PAWS-TF/models/wide_resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · 40d8c0a153356fd9 · report

Tasks

Image ClassificationPseudo LabelSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet PAWS (ResNet-50, 10% labels) Top 1 Accuracy 75.5% #946 of 1060 Archive leaderboard report
Image Classification ImageNet PAWS (ResNet-50, 1% labels) Top 1 Accuracy 66.5% #1042 of 1060 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels PAWS-NN (WRN-28-2) Percentage error 4.0 ± 0.25 #7 of 49 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data PAWS (ResNet-50 4x) Top 1 Accuracy 69.9% #21 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data PAWS (ResNet-50 2x) Top 1 Accuracy 69.6% #22 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data PAWS (ResNet-50) Top 1 Accuracy 66.5% #29 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data PAWS (ResNet-50 4x) Top 1 Accuracy 79.0% #14 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data PAWS (ResNet-50 2x) Top 1 Accuracy 77.8% #19 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data PAWS (ResNet-50) Top 1 Accuracy 75.5% #25 of 75 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

BYOLLARSSwAV

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