Papers › Compressive Visual Representations

Compressive Visual Representations

27 Sep 2021NeurIPS 2021 12arXiv:2109.12909archive 2025-07-28

Kuang-Huei Lee, Anurag Arnab, Sergio Guadarrama, John Canny, Ian Fischer

Learning effective visual representations that generalize well without human supervision is a fundamental problem in order to apply Machine Learning to a wide variety of tasks. Recently, two families of self-supervised methods, contrastive learning and latent bootstrapping, exemplified by SimCLR and BYOL respectively, have made significant progress. In this work, we hypothesize that adding explicit information compression to these algorithms yields better and more robust representations. We verify this by developing SimCLR and BYOL formulations compatible with the Conditional Entropy Bottleneck (CEB) objective, allowing us to both measure and control the amount of compression in the learned representation, and observe their impact on downstream tasks. Furthermore, we explore the relationship between Lipschitz continuity and compression, showing a tractable lower bound on the Lipschitz constant of the encoders we learn. As Lipschitz continuity is closely related to robustness, this provides a new explanation for why compressed models are more robust. Our experiments confirm that adding compression to SimCLR and BYOL significantly improves linear evaluation accuracies and model robustness across a wide range of domain shifts. In particular, the compressed version of BYOL achieves 76.0% Top-1 linear evaluation accuracy on ImageNet with ResNet-50, and 78.8% with ResNet-50 2x.

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="2109.12909")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: official repository: 12 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

google-research/compressive-visual-representations officialmentioned in papermentioned 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

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 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.

12unverified

Licence: 0 of the 12 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 google-research/compressive-visual-representations. “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.

add_contrastive_loss google-research/compressive-visual-representations/compressive_visual_representations/objective.py official repository unverified Apache-2.0 (permissive) · 2c3f186a80593c53 · report
add_supervised_loss google-research/compressive-visual-representations/compressive_visual_representations/objective.py official repository unverified Apache-2.0 (permissive) · 1029520ddfa4b329 · report
add_weight_decay google-research/compressive-visual-representations/compressive_visual_representations/model_util.py official repository unverified Apache-2.0 (permissive) · bf0a0bdd5fe4e8e0 · report
arg_natural_sort google-research/compressive-visual-representations/compressive_visual_representations/model.py official repository unverified Apache-2.0 (permissive) · 2b7c6aa449d316cc · report
cosine_ramping_schedule google-research/compressive-visual-representations/compressive_visual_representations/model_util.py official repository unverified Apache-2.0 (permissive) · 7182c3d894d78468 · report
get_train_steps google-research/compressive-visual-representations/compressive_visual_representations/model_util.py official repository unverified Apache-2.0 (permissive) · 14ec8ff095316493 · report
natural_key google-research/compressive-visual-representations/compressive_visual_representations/model.py official repository unverified Apache-2.0 (permissive) · 53256e57b7ff1522 · report
random_apply google-research/compressive-visual-representations/compressive_visual_representations/data_util.py official repository unverified Apache-2.0 (permissive) · 293ca4cd93119d57 · report
random_brightness google-research/compressive-visual-representations/compressive_visual_representations/data_util.py official repository unverified Apache-2.0 (permissive) · 35f2f206e2a2532c · report
resnet google-research/compressive-visual-representations/compressive_visual_representations/resnet.py official repository unverified Apache-2.0 (permissive) · 808316afe07e1036 · report
to_grayscale google-research/compressive-visual-representations/compressive_visual_representations/data_util.py official repository unverified Apache-2.0 (permissive) · 661534bbe78e800f · report
tpu_cross_replica_concat google-research/compressive-visual-representations/compressive_visual_representations/objective.py official repository unverified Apache-2.0 (permissive) · cb79992de5bf735c · report

Tasks

Contrastive LearningImage ClassificationLinear evaluationSelf-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ObjectNet C-BYOL Top-1 Accuracy 25.5 #81 of 106 Archive leaderboard report
Image Classification ObjectNet C-SimCLR Top-1 Accuracy 20.8 #89 of 106 Archive leaderboard report
Self-Supervised Image Classification ImageNet C-BYOL (ResNet-50 2x, 1000 epochs) Number of Params 94M #41 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet C-BYOL (ResNet-50 2x, 1000 epochs) Top 1 Accuracy 78.8% #41 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet C-BYOL (ResNet-50 2x, 1000 epochs) Top 5 Accuracy 94.5% #41 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet C-BYOL (ResNet-50, 1000 epochs) Number of Params 25M #70 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet C-BYOL (ResNet-50, 1000 epochs) Top 1 Accuracy 75.6% #70 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet C-BYOL (ResNet-50, 1000 epochs) Top 5 Accuracy 92.7% #70 of 144 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

1x1 ConvolutionAverage PoolingBYOLBatch NormalizationBottleneck Residual BlockColorJitterContrastive LearningConvolutionDense ConnectionsFeedforward NetworkGlobal Average PoolingKaiming InitializationMax PoolingNT-XentRandom Gaussian BlurRandom Resized CropReLUResidual BlockResidual ConnectionSimCLR

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