Papers › MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter
We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in intermediate layers. Accordingly, MIM-Refiner leverages multiple contrastive heads that are connected to different intermediate layers. In each head, a modified nearest neighbor objective constructs semantic clusters that capture semantic information which improves performance on downstream tasks, including off-the-shelf and fine-tuning settings. The refinement process is short and simple - yet highly effective. Within a few epochs, we refine the features of MIM models from subpar to state-of-the-art, off-the-shelf features. Refining a ViT-H, pre-trained with data2vec 2.0 on ImageNet-1K, sets a new state-of-the-art in linear probing (84.7%) and low-shot classification among models that are pre-trained on ImageNet-1K. MIM-Refiner efficiently combines the advantages of MIM and ID objectives and compares favorably against previous state-of-the-art SSL models on a variety of benchmarks such as low-shot classification, long-tailed classification, clustering and semantic segmentation.
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="2402.10093")
Code
Syntology Ran 3 of 3 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran with no contract checked.
By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
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
3 samples harvested; 3 ran; 0 honoured the contract we drafted; 0 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: 0 of the 3 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 2 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.
e016ec63c51a6da2 · report
f6c53a7cbc1b6bab · report
4ab6e53ac50164ed · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Clustering | ImageNet | MIM-Refiner (D2V2-ViT-H/14) | ARI | 42.2 | #2 of 12 | Archive leaderboard | report |
| Image Clustering | ImageNet | MIM-Refiner (D2V2-ViT-H/14) | Accuracy | 67.3 | #2 of 12 | Archive leaderboard | report |
| Image Clustering | ImageNet | MIM-Refiner (D2V2-ViT-H/14) | NMI | 87.2 | #2 of 12 | Archive leaderboard | report |
| Image Clustering | ImageNet | MIM-Refiner (MAE-ViT-H/14) | ARI | 45.5 | #4 of 12 | Archive leaderboard | report |
| Image Clustering | ImageNet | MIM-Refiner (MAE-ViT-H/14) | Accuracy | 64.6 | #4 of 12 | Archive leaderboard | report |
| Image Clustering | ImageNet | MIM-Refiner (MAE-ViT-H/14) | NMI | 85.3 | #4 of 12 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (D2V2-ViT-H/14) | Number of Params | 632M | #5 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (D2V2-ViT-H/14) | Top 1 Accuracy | 84.7% | #5 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (MAE-ViT-2B/14) | Number of Params | 1890M | #6 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (MAE-ViT-2B/14) | Top 1 Accuracy | 84.5% | #6 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (MAE-ViT-H/14 | Number of Params | 632M | #8 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (MAE-ViT-H/14 | Top 1 Accuracy | 83.7% | #8 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (D2V2-ViT-L/16) | Number of Params | 307M | #9 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (D2V2-ViT-L/16) | Top 1 Accuracy | 83.5% | #9 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (MAE-ViT-L/16) | Number of Params | 307M | #10 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | MIM-Refiner (MAE-ViT-L/16) | Top 1 Accuracy | 82.8% | #10 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
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