Papers › Exploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation Learning
Xinlei Chen, Kaiming He
Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for avoiding collapsing solutions. In this paper, we report surprising empirical results that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders. Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing. We provide a hypothesis on the implication of stop-gradient, and further show proof-of-concept experiments verifying it. Our "SimSiam" method achieves competitive results on ImageNet and downstream tasks. We hope this simple baseline will motivate people to rethink the roles of Siamese architectures for unsupervised representation learning. Code will be made available.
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="2011.10566")
Code
Syntology Ran 34 of 39 code samples harvested from 11 repositories linked to this paper; 5 have no recorded run. Of those that ran: 7 ran · our draft was wrong; 2 ran · fixture could not drive it; 25 ran with no contract checked.
By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 37 samples from 10 repositories, 32 ran; 1 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.
26 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
39 samples harvested; 34 ran; 0 honoured the contract we drafted; 5 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: 22 of the 39 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 11 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.
492cc68fb1110aa3 · report
47df0764b5090ea2 · report
bbe4c4713c60cb7b · report
4d45d7d0856d7377 · report
b2429807c9efa3f7 · report
dc05a6f71458b31e · report
38628e7af88c5ed9 · report
6bd663b5be82dccd · report
bb30a29172efa151 · report
516cd76945c13b46 · report
9d0e6a2eca652065 · report
da76a8285671b345 · report
0f2aaed67b1fc0a0 · report
ed0e4015879df242 · report
e6da00517c19b39c · report
4a6376067215c5f6 · report
efbcdfcbc565884f · report
1ace917fd995e564 · report
009322dbbfd98763 · report
815591f7486b47ff · report
d9b4a10391a8d49f · report
5ef921dde450036d · report
fb0cb8a440e873f9 · report
32880b6d81ed25f9 · report
752e4e769526a23c · report
7aa59b2768a14009 · report
4e65e79a1e2a3fcc · report
012204ec88654334 · report
baecb6445a98aac2 · report
d23738a6312f956e · report
18a041c1ad13c81f · report
4f89fc5dcdf63603 · report
4eff742841c262a2 · report
bd3b410047cb6c47 · report
f2af91921deea94a · report
c9eb23d22a1f6e19 · report
1a35ab02b0214a3a · report
cb99b702c75951a5 · report
971ae8d2d8313e30 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Self-Supervised Image Classification | ImageNet | SimSiam (ResNet-50) | Number of Params | 24M | #99 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | SimSiam (ResNet-50) | Top 1 Accuracy | 71.3% | #99 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.
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