Papers › Improved Baselines with Momentum Contrastive Learning
Improved Baselines with Momentum Contrastive Learning
Xinlei Chen, Haoqi Fan, Ross Girshick, Kaiming He
Contrastive unsupervised learning has recently shown encouraging progress, e.g., in Momentum Contrast (MoCo) and SimCLR. In this note, we verify the effectiveness of two of SimCLR's design improvements by implementing them in the MoCo framework. With simple modifications to MoCo---namely, using an MLP projection head and more data augmentation---we establish stronger baselines that outperform SimCLR and do not require large training batches. We hope this will make state-of-the-art unsupervised learning research more accessible. Code will be made public.
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="2003.04297")
Code
Syntology Ran 8 of 43 code samples harvested from 6 repositories linked to this paper; 35 have no recorded run. Of those that ran: 1 ran · violated contract; 3 ran · our draft was wrong; 4 ran · fixture could not drive it.
By repository: community (archive-listed): 37 samples from 6 repositories, 5 ran; 6 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.
36 repositories listed; official and paper-mentioned ones first.
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
43 samples harvested; 8 ran; 0 honoured the contract we drafted; 35 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.
Licence: 10 of the 43 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 6 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.
06532ecb66c0bcf9 · report
2a80220dabcb742a · report
600ff2c45e0de056 · report
7c29b374198bddcd · report
4dd7c3cff0150cb9 · report
c877664f0b6c29ba · report
3b69089e7dfcef76 · report
82c869e73df33e11 · report
e31ff5999b5f7a9f · report
0def50a351111624 · report
129adedbc3f353c4 · report
a2ae53d34bc13317 · report
c6c33546958d1759 · report
96aec64c84c32d81 · report
b615a4c82ed53c29 · report
3a56153874d5df28 · report
ada42cd4264e001d · report
5636af1506db32d1 · report
f8f9437c5a9c0588 · report
e9cdcc13fe49820c · report
045e7fb3560388d4 · report
2da6bd8937cdb982 · report
60ae2cf6b5924c2d · report
5f912135342a1eac · report
c3f9a96837f42be0 · report
1941df4f816178f1 · report
c26e2d748dacb750 · report
efba4631d8880f62 · report
580cd13eb9675631 · report
5c153d8093022479 · report
1d3bcae9b7aa7920 · report
d444d3b77bdf398b · report
35ee0a5ef1232571 · report
07f548c71e7969f6 · report
efad379ea20fec59 · report
8685ce39337a0ffc · report
3d39d5577a13c30e · report
983576fa67f4f01e · report
131a82fd65128218 · report
63ce1d5edf8fb0a0 · report
9b8289076669fe4f · report
73cecca9f3575f09 · report
0358792e34e9cbb2 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Contrastive Learning | imagenet-1k | ResNet50 | ImageNet Top-1 Accuracy | 71.1 | #3 of 14 | Archive leaderboard | report |
| Image Classification | Places205 | MoCo v2 | Top 1 Accuracy | 52.9 | #15 of 15 | Archive leaderboard | report |
| Person Re-Identification | SYSU-30k | MoCo v2 (self-supervised) | Rank-1 | 11.6 | #6 of 10 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MoCo v2 (ResNet-50) | Number of Params | 24M | #100 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MoCo v2 (ResNet-50) | Top 1 Accuracy | 71.1% | #100 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MoCo v2 (ResNet-50) | Top 5 Accuracy | 90.1% | #100 of 144 | Archive leaderboard | report |
| Self-Supervised Person Re-Identification | SYSU-30k | MoCo v2 | Rank-1 | 11.6 | #3 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
Introduced by this paper: MoCo v2
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