SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.01489 · ICCV · 2023

Improved Visual Fine-tuning with Natural Language Supervision

Ming Yan, Qi Qian, Yuanhong Xu, Juhua Hu, Junyang Wang, Jitao Sang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 1 failure of our instrument; 0 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/2304.01489.json · badge: /api/ran/2304.01489.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
idstcv/TeS community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
TeS_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
idstcv/TeS/TeS_loss.py
code served (permissive licence) · get_code("e9885b090e2c9dd7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define a small model that produces the required outputs
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, output_dim=3, proj_dim=5):
        super().__init__()
        self.fc = nn.Linear(input_dim, output_dim)
        self.proj = nn.Linear(input_dim, proj_dim)
    
    def forward(self, x):
        return {
            'x': self.fc(x),
            'x_proj': self.proj(x)
        }

# Create model and get sample output
model = SimpleModel(input_dim=4, output_dim=3, proj_dim=5)
batch_size = 2
input_tensor = torch.randn(batch_size, 4)
model_output = model(input_tensor)

# Create text features (num_classes x proj_dim)
num_classes = 3
text_feature = torch.randn(num_classes, 5)

# Create target labels
target = torch.tensor([0, 1])

# Create criterion (CrossEntropyLoss)
criterion = nn.CrossEntropyLoss()

# Create hyperparameters
tau = 0.1
lambda_v = 0.5
lambda_t = 0.3

ARGS = {
    'text_feature': text_feature,
    'model_output': model_output,
    'target': target,
    'criterion': criterion,
    'tau': tau,
    'lambda_v': lambda_v,
    'lambda_t': lambda_t
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of catastrophic forgetting in pre-trained backbone has been extensively studied for fine-tuning, its potential bias from the corresponding pre-training task and data, attracts less attention. In this work, we investigate this problem by demonstrating that the obtained classifier after fine-tuning will be close to that induced by the pre-trained model. To reduce the bias in the classifier effectively, we introduce a reference distribution obtained from a fixed text classifier, which can help regularize the learned vision classifier. The proposed method, Text Supervised fine-tuning (TeS), is evaluated with diverse pre-trained vision models including ResNet and ViT, and text encoders including BERT and CLIP, on 11 downstream tasks. The consistent improvement with a clear margin over distinct scenarios confirms the effectiveness of our proposal. Code is available at https://github.com/idstcv/TeS.

For agents

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

get_harvested_code_for_paper("2304.01489")
get_code_for_paper("2304.01489")
have("2304.01489")

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

curl https://syntology.ai/api/ran/2304.01489.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.01489.svg)](https://syntology.ai/paper/2304.01489)

Connect an agent — have() is free.