Papers › ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation

ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation

7 Dec 2022CVPR 2023 1arXiv:2212.03588archive 2025-07-28

Ziqin Zhou, BoWen Zhang, Yinjie Lei, Lingqiao Liu, Yifan Liu

Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme. The general idea is to first generate class-agnostic region proposals and then feed the cropped proposal regions to CLIP to utilize its image-level zero-shot classification capability. While effective, such a scheme requires two image encoders, one for proposal generation and one for CLIP, leading to a complicated pipeline and high computational cost. In this work, we pursue a simpler-and-efficient one-stage solution that directly extends CLIP's zero-shot prediction capability from image to pixel level. Our investigation starts with a straightforward extension as our baseline that generates semantic masks by comparing the similarity between text and patch embeddings extracted from CLIP. However, such a paradigm could heavily overfit the seen classes and fail to generalize to unseen classes. To handle this issue, we propose three simple-but-effective designs and figure out that they can significantly retain the inherent zero-shot capacity of CLIP and improve pixel-level generalization ability. Incorporating those modifications leads to an efficient zero-shot semantic segmentation system called ZegCLIP. Through extensive experiments on three public benchmarks, ZegCLIP demonstrates superior performance, outperforming the state-of-the-art methods by a large margin under both "inductive" and "transductive" zero-shot settings. In addition, compared with the two-stage method, our one-stage ZegCLIP achieves a speedup of about 5 times faster during inference. We release the code at https://github.com/ZiqinZhou66/ZegCLIP.git.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 9 ran (5 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ZiqinZhou66/ZegCLIP officialmentioned in papermentioned on GitHubpytorchMITSyntology: 9 samples, 9 ran (4 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
3ran

Licence: 3 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ZiqinZhou66/ZegCLIP. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ZiqinZhou66/ZegCLIP official repository 9 samples, 9 ran (4 instrument-failed) · 0 unverified
basic_clean in 217 papers models/segmentor/untils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
cosine_margin_loss models/losses/criterion.py ran MIT (permissive) · 864ff812c98727df · report fixture: signature q:Tensor/3/float, e:Tensor/2/float, labels:Tensor/1/int, tau:float/0/float, m:float/0/float · returned Tensor · level recorded 2026-09-24
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
models/losses/criterion.py ran fingerprinted MIT (permissive) · 016dba4163da28df · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:int/0/int · returned Tensor · level recorded 2026-09-24
get_angles in 21 papers
census: 3 implementations from 7 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind int, dtype int32
models/decode_heads/utils.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 7816c6d65ab55d8f · report fixture: signature pos:ndarray/2/float, i:ndarray/2/int, d_model:int/0/int · returned ndarray · level recorded 2026-09-22
get_pairs in 260 papers models/segmentor/untils.py ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
nested_tensor_from_tensor_list in 60 papers models/losses/misc.py ran · our draft was wrong MIT (permissive) · 58cc9ff3bf75e753 · report fixture: signature tensor_list:list/1/Tensor · returned NestedTensor · level recorded 2026-09-25
positional_encoding in 63 papers
census: 5 implementations from 6 papers, 4 distinct outputs on one shared input
models/decode_heads/utils.py ran · honoured contract MIT (permissive) · da3acf7173bd84f0 · report fixture: signature position:int/0/int, d_model:int/0/int · returned ndarray · level recorded 2026-09-24
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
models/losses/criterion.py ran fingerprinted MIT (permissive) · 2675e89c94ae08bf · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-24
whitespace_clean in 230 papers models/segmentor/untils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22

Tasks

Semantic SegmentationZero-Shot LearningZero-Shot Semantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Semantic Segmentation COCO-Stuff ZegCLIP Inductive Setting hIoU 40.8 #4 of 15 Archive leaderboard report
Zero-Shot Semantic Segmentation COCO-Stuff ZegCLIP Transductive Setting hIoU 48.5 #4 of 15 Archive leaderboard report
Zero-Shot Semantic Segmentation PASCAL VOC ZegCLIP Inductive Setting hIoU 84.3 #4 of 13 Archive leaderboard report
Zero-Shot Semantic Segmentation PASCAL VOC ZegCLIP Transductive Setting hIoU 91.1 #4 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CLIPfail

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections