SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.02460 · CVPR · 2024

Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions

Oindrila Saha, Grant Horn, Subhransu Maji

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 0 have no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2401.02460.json · badge: /api/ran/2401.02460.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
cvl-umass/AdaptCLIPZS canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
get_family Ran
ran; our contract draft was wrong, not the code
cvl-umass/AdaptCLIPZS/utils_nat.py
pointer only (licence: NONE) · get_code("912ffb0c9811febb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvl-umass/AdaptCLIPZS when it was checked. 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.

get_order Ran
ran; our contract draft was wrong, not the code
cvl-umass/AdaptCLIPZS/utils_nat.py
pointer only (licence: NONE) · get_code("82486e06c539f2a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvl-umass/AdaptCLIPZS when it was checked. 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.

get_scientific_name Ran
ran; our contract draft was wrong, not the code
cvl-umass/AdaptCLIPZS/utils_nat.py
pointer only (licence: NONE) · get_code("c7e6a327921934d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvl-umass/AdaptCLIPZS when it was checked. 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.

read_json Ran
ran; our contract draft was wrong, not the code
cvl-umass/AdaptCLIPZS/vdt_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from luomingshuang/M3GPT, is pointer only (licence: NONE) · get_code("7d6e263caea8e963")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvl-umass/AdaptCLIPZS when it was checked. 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.

read_split Ran
ran; our contract draft was wrong, not the code
cvl-umass/AdaptCLIPZS/vdt_utils.py
pointer only (licence: NONE) · get_code("0fb1c181d94319b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cvl-umass/AdaptCLIPZS when it was checked. 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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
read_json 8 other papers
6 dated earlier, 1 later, 1 same year, order not determinable
1612.05601 (2016-12)
SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound
1903.11306 (2019-03)
Linkage Based Face Clustering via Graph Convolution Network
2001.04193 (2020-01)
Deep Learning for Person Re-identification: A Survey and Outlook
and 5 more not named here

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 2026-11-21.

Repositories linked to this paper

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

Abstract

The zero-shot performance of existing vision-language models (VLMs) such as CLIP [29] is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources of information-descriptions of categories generated by large language models (LLMs) and abundant, fine-grained image classification datasets-to improve the zero-shot classification performance of VLMs across finegrained domains. On the technical side, we develop methods to train VLMs with this "bag-level" image-text supervision. We find that simply using these attributes at testtime does not improve performance, but our training strategy, for example, on the iNaturalist [41] dataset, leads to an average improvement of 4-5% in zero-shot classification accuracy for novel categories of birds [42] and flowers [23]. Similar improvements are observed in domains where a subset of the categories was used to fine-tune the model. By prompting LLMs in various ways, we generate descriptions that capture visual appearance, habitat, and geographic regions and pair them with existing attributes such as the taxonomic structure of the categories. We systematically evaluate their ability to improve zero-shot categorization in natural domains. Our findings suggest that geographic priors can be just as effective and are complementary to visual appearance. Our method also outperforms prior work on prompt-based tuning of VLMs. We release the benchmark, consisting of 14 datasets at https: //github.com/cvl-umass/AdaptCLIPZS, which will contribute to future research in zero-shot recognition.

For agents

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

get_harvested_code_for_paper("2401.02460")
get_code_for_paper("2401.02460")
have("2401.02460")

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

curl https://syntology.ai/api/ran/2401.02460.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.02460.svg)](https://syntology.ai/paper/2401.02460)

Connect an agent — have() is free.