SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.02487 · NeurIPS · 2023

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Qihang Yu, Liang-Chieh Chen, Ju He, Xueqing Deng, Xiaohui Shen

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 1 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/2308.02487.json · badge: /api/ran/2308.02487.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
bytedance/fc-clip canonical (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
loadAde20K Ran
ran; our contract draft was wrong, not the code
bytedance/fc-clip/datasets/prepare_ade20k_full_sem_seg.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from jiaosiyu1999/MAFT, is pointer only (licence: NONE) · get_code("6935590148878098")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from jiaosiyu1999/MAFT, and GitHub detected no licence in that repository 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.

generate_labels Not yet run
unverified (harvested, no recorded run)
bytedance/fc-clip/datasets/prepare_pascal_ctx_sem_seg.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from jiaosiyu1999/MAFT, is pointer only (licence: NONE) · get_code("cb6dcd02dbb95f73")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from jiaosiyu1999/MAFT, and GitHub detected no licence in that repository 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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
loadAde20K 2 other papers
1 dated earlier, 1 later
2303.11797 (2023-03)
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
2310.00240 (2023-10)
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation
generate_labels 1 other paper
1 later
2310.00240 (2023-10)
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation

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

Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories in diverse environments. One way to address this challenge is to leverage multi-modal models, such as CLIP, to provide image and text features in a shared embedding space, which effectively bridges the gap between closed-vocabulary and open-vocabulary recognition. Hence, existing methods often adopt a two-stage framework to tackle the problem, where the inputs first go through a mask generator and then through the CLIP model along with the predicted masks. This process involves extracting features from raw images multiple times, which can be ineffective and inefficient. By contrast, we propose to build everything into a single-stage framework using a shared Frozen Convolutional CLIP backbone, which not only significantly simplifies the current two-stage pipeline, but also remarkably yields a better accuracy-cost trade-off. The resulting single-stage system, called FC-CLIP, benefits from the following observations: the frozen CLIP backbone maintains the ability of open-vocabulary classification and can also serve as a strong mask generator, and the convolutional CLIP generalizes well to a larger input resolution than the one used during contrastive image-text pretraining. Surprisingly, FC-CLIP advances state-of-the-art results on various benchmarks, while running practically fast. Specifically, when training on COCO panoptic data only and testing in a zero-shot manner,

For agents

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

get_harvested_code_for_paper("2308.02487")
get_code_for_paper("2308.02487")
have("2308.02487")

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

curl https://syntology.ai/api/ran/2308.02487.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.02487.svg)](https://syntology.ai/paper/2308.02487)

Connect an agent — have() is free.