SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.06809 · ICLR · 2024

DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks

Ser-Nam Lim, Amin Karimi Monsefi, Kishore Prakash Sailaja, Ali Alilooee, Rajiv Ramnath

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 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 2 have no contract verdict; 4 failures of our instrument; 5 no recorded run), measured 2026-11-22; 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/2409.06809.json · badge: /api/ran/2409.06809.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
KishoreP1/DetailCLIP canonical (classifier label)
classifier basis: classifier_2025
6 ran · 5 no recorded run
FunctionStatusWhere it lives
CLIP Ran
ran on a synthesized input
KishoreP1/DetailCLIP/models.py
pointer only (licence: NONE) · get_code("8d7b5685c27c8566")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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.

CSyncBatchNorm Ran
ran on a synthesized input
KishoreP1/DetailCLIP/models.py
pointer only (licence: NONE) · get_code("c33ed4816cfeb73f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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.

accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KishoreP1/DetailCLIP/eval_zeroshot.py
pointer only (licence: NONE) · get_code("2e59707d16d21473")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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.

extract Ran
ran; our contract draft was wrong, not the code
KishoreP1/DetailCLIP/extract_backbone_weights.py
pointer only (licence: NONE) · get_code("4f14f3e2415a28c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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_att_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KishoreP1/DetailCLIP/models.py
pointer only (licence: NONE) · get_code("f8278dbfe57c1b58")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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.

mean_per_class Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KishoreP1/DetailCLIP/eval_zeroshot.py
pointer only (licence: NONE) · get_code("f0eb8193f86d363b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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.

CustomSequential Not yet run
unverified (harvested, no recorded run)
KishoreP1/DetailCLIP/models.py
pointer only (licence: NONE) · get_code("39a3b3f9967fdec3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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. No invocation recorded.

DINOHead Not yet run
unverified (harvested, no recorded run)
KishoreP1/DetailCLIP/models.py
pointer only (licence: NONE) · get_code("1fe58b925a6046d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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. No invocation recorded.

DetailCLIP Not yet run
unverified (harvested, no recorded run)
KishoreP1/DetailCLIP/models.py
pointer only (licence: NONE) · get_code("857796c6313780ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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. No invocation recorded.

PSyncBatchNorm Not yet run
unverified (harvested, no recorded run)
KishoreP1/DetailCLIP/models.py
pointer only (licence: NONE) · get_code("90448ee89aa26b11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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. No invocation recorded.

iBOTHead Not yet run
unverified (harvested, no recorded run)
KishoreP1/DetailCLIP/models.py
pointer only (licence: NONE) · get_code("16d539a3bde9714a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KishoreP1/DetailCLIP 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. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 6 later) and 3 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
accuracy 13 other papers
12 dated earlier, 1 later
1706.02677 (2017-06)
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
1911.00068 (2019-11)
Confident Learning: Estimating Uncertainty in Dataset Labels
2011.09157 (2020-11)
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
and 10 more not named here
mean_per_class 5 other papers
5 dated earlier
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2112.12750 (2021-12)
SLIP: Self-supervision meets Language-Image Pre-training
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
and 2 more not named here
CSyncBatchNorm
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2503.15141 (2025-03)
Object-Centric Pretraining via Target Encoder Bootstrapping
CustomSequential
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2503.15141 (2025-03)
Object-Centric Pretraining via Target Encoder Bootstrapping
DINOHead
brick of this paper's assembly: helper
1 other paper
1 later
2503.15141 (2025-03)
Object-Centric Pretraining via Target Encoder Bootstrapping
PSyncBatchNorm
brick of this paper's assembly: helper
1 other paper
1 later
2503.15141 (2025-03)
Object-Centric Pretraining via Target Encoder Bootstrapping
get_att_mask
brick of this paper's assembly: helper
1 other paper
1 dated earlier
Yang_Attentive_Mask_CLIP_ICCV_2023_paper (2023 (year only))
Attentive Mask CLIP
iBOTHead
brick of this paper's assembly: helper
1 other paper
1 later
2503.15141 (2025-03)
Object-Centric Pretraining via Target Encoder Bootstrapping

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

In this paper, we introduce DetailCLIP, a self-improving vision-language foundation model designed to enhance fine-grained feature understanding through selfsupervised learning. Foundation models like CLIP have demonstrated strong performance in global image-text alignment but often fail to capture detail-oriented features necessary for tasks such as segmentation. To address this, DetailCLIP integrates self-curated learning objectives that iteratively improve both high-level semantics and detailed visual representations. Specifically, our method employs patch-level self-distillation and pixel-level reconstruction losses to generate refined internal representations, while an attention-based token filtering mechanism curates semantically relevant information during training. By generating and refining self-curated learning signals, DetailCLIP improves segmentation performance and demonstrates superior generalization across diverse tasks. These taskagnostic objectives position DetailCLIP as a self-improving foundation model, enhancing multi-modal systems like CLIP with fine-grained feature understanding. https://github.com/KishoreP1/DetailCLIP * Equal contribution.

For agents

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

get_harvested_code_for_paper("2409.06809")
get_code_for_paper("2409.06809")
have("2409.06809")

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

curl https://syntology.ai/api/ran/2409.06809.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.06809.svg)](https://syntology.ai/paper/2409.06809)

Connect an agent — have() is free.