SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.09445 · 2021

Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2112.09445.json · badge: /api/ran/2112.09445.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
facebookresearch/otter canonical (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
FunctionStatusWhere it lives
add_weight_decay Ran
ran; our contract draft was wrong, not the code
facebookresearch/otter/optim/optim_factory.py
pointer only (licence: MIT); the stored copy get_code serves, from HaiyangZheng/PHE, is pointer only (licence: NONE) · get_code("b40701674badc944")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/otter, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_optimizer Ran
ran on a synthesized input
facebookresearch/otter/optim/optim_factory.py
pointer only (licence: MIT) · get_code("c1d6a1762ac426cb")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/otter, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

on_diag_avg Ran
ran on a synthesized input
facebookresearch/otter/dataset_analysis.py
pointer only (licence: MIT) · get_code("20ce03a3068a692a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/otter, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sinkhorn Ran
ran on a synthesized input
facebookresearch/otter/models/model_util.py
pointer only (licence: MIT) · get_code("470b932b453c7bbe")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/otter, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

off_diag_avg Not yet run
unverified (harvested, no recorded run)
facebookresearch/otter/dataset_analysis.py
pointer only (licence: MIT) · get_code("9fbdbe606c3381f5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/otter, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

off_diag_max Not yet run
unverified (harvested, no recorded run)
facebookresearch/otter/dataset_analysis.py
pointer only (licence: MIT) · get_code("d0761aacd8d0e3de")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/otter, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
add_weight_decay 3 other papers
3 later
2403.07560 (2024-03)
Unleashing Network Potentials for Semantic Scene Completion
2403.19589 (2024-03)
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
2410.19213 (2024-10)
Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts than supervised "gold" labels. Previous works, such as CLIP, use InfoNCE loss to train a model to predict the pairing between images and text captions. CLIP, however, is data hungry and requires more than 400M image-text pairs for training. The inefficiency can be partially attributed to the fact that the image-text pairs are noisy. To address this, we propose OTTER (Optimal TransporT distillation for Efficient zero-shot Recognition), which uses online entropic optimal transport to find a soft image-text match as labels for contrastive learning. Based on pretrained image and text encoders, models trained with OTTER achieve strong performance with only 3M image text pairs. Compared with InfoNCE loss, label smoothing, and knowledge distillation, OTTER consistently outperforms these baselines in zero shot evaluation on Google Open Images (19,958 classes) and multi-labeled ImageNet 10K (10032 classes) from Tencent ML-Images. Over 42 evaluations on 7 different dataset/architecture settings x 6 metrics, OTTER outperforms (32) or ties (2) all baselines in 34 of them.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2112.09445")
get_code_for_paper("2112.09445")
have("2112.09445")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2112.09445.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2112.09445.svg)](https://syntology.ai/paper/2112.09445)

Connect an agent — have() is free.