Papers › No Reason for No Supervision: Improved Generalization in Supervised Models

No Reason for No Supervision: Improved Generalization in Supervised Models

30 Jun 2022arXiv:2206.15369archive 2025-07-28

Mert Bulent Sariyildiz, Yannis Kalantidis, Karteek Alahari, Diane Larlus

We consider the problem of training a deep neural network on a given classification task, e.g., ImageNet-1K (IN1K), so that it excels at both the training task as well as at other (future) transfer tasks. These two seemingly contradictory properties impose a trade-off between improving the model's generalization and maintaining its performance on the original task. Models trained with self-supervised learning tend to generalize better than their supervised counterparts for transfer learning; yet, they still lag behind supervised models on IN1K. In this paper, we propose a supervised learning setup that leverages the best of both worlds. We extensively analyze supervised training using multi-scale crops for data augmentation and an expendable projector head, and reveal that the design of the projector allows us to control the trade-off between performance on the training task and transferability. We further replace the last layer of class weights with class prototypes computed on the fly using a memory bank and derive two models: t-ReX that achieves a new state of the art for transfer learning and outperforms top methods such as DINO and PAWS on IN1K, and t-ReX* that matches the highly optimized RSB-A1 model on IN1K while performing better on transfer tasks. Code and pretrained models: https://europe.naverlabs.com/t-rex

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

naver/trex mentioned on GitHubpytorchSyntology: 9 samples, 7 ran (1 instrument-failed) · 2 unverified 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

9 samples harvested: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
6ran
2unverified

Licence: 9 of the 9 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 naver/trex. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

naver/trex community (archive-listed) 9 samples, 7 ran (1 instrument-failed) · 2 unverified
ClfLayer trex.py ran · metamorphic tier: deterministic licence not identified · pointer only · 41116699c46b3310 · report fixture: returned ClfLayer · level recorded 2026-09-22
L2Norm trex.py ran · metamorphic tier: deterministic licence not identified · pointer only · 4cb0ee0916149068 · report fixture: returned L2Norm · level recorded 2026-09-22
MLPLayer in 15 papers trex.py ran · metamorphic tier: deterministic licence not identified · pointer only · 1c58a693c3409799 · report fixture: returned MLPLayer · level recorded 2026-09-22
Memory in 19 papers trex.py ran · metamorphic tier: deterministic licence not identified · pointer only · 970137f4cfb773bd · report fixture: returned Memory · level recorded 2026-09-22
MultiCropWrapper trex.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 425be11095e5f61e · report fixture: returned MultiCropWrapper · level recorded 2026-09-22
Projector in 18 papers trex.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 3983640112d8f466 · report fixture: returned Projector · level recorded 2026-09-22
make_model in 37 papers trex.py ran · our draft was wrong licence not identified · pointer only · e03caab433c9fa61 · report fixture: signature arch:str/0/str, proj_input_l2_norm:bool/0/bool, proj_hidden_layers:int/0/int, proj_hidden_dim:int/0/int, proj_bottleneck_dim:int/0/int · returned MultiCropWrapper · level recorded 2026-09-22
init_weights in 109 papers trex.py unverified licence not identified · pointer only · 0f95b3a63fa2e010 · report
tReX trex.py unverified licence not identified · pointer only · 78aa378e6f1154e7 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for t-ReX (graph method: t-ReX). 10 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. tReX entry · level 0 · unverified · 78aa378e6f1154e7
  2. ClfLayer model · level 1 · ran · 41116699c46b3310
  3. L2Norm helper · level 1 · ran · 4cb0ee0916149068
  4. Memory helper · level 1 · ran · 970137f4cfb773bd
  5. make_model helper · level 1 · ran · our draft was wrong · e03caab433c9fa61
  6. concat_all_gather helper · level 0 · unverified · a2ae53d34bc13317
  7. MultiCropWrapper helper · level 1 · ran · 425be11095e5f61e
  8. Projector model · level 1 · ran · 3983640112d8f466
  9. init_weights helper · level 0 · unverified · 0f95b3a63fa2e010
  10. MLPLayer helper · level 1 · ran · 1c58a693c3409799

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2206.15369") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationSelf-Supervised LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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