Papers › CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for...

CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation

15 Nov 2024arXiv:2411.10086archive 2025-07-28

Dengke Zhang, Fagui Liu, Quan Tang

Open-vocabulary semantic segmentation aims to assign semantic labels to each pixel without relying on a predefined set of categories. Contrastive Language-Image Pre-training (CLIP) demonstrates outstanding zero-shot classification capabilities but struggles with the pixel-wise segmentation task as the captured inter-patch correlations correspond to no specific visual concepts. Despite previous CLIP-based works improving inter-patch correlations by self-self attention, they still face the inherent limitation that image patches tend to have high similarity to outlier ones. In this work, we introduce CorrCLIP, a training-free approach for open-vocabulary semantic segmentation, which reconstructs significantly coherent inter-patch correlations utilizing foundation models. Specifically, it employs the Segment Anything Model (SAM) to define the scope of patch interactions, ensuring that patches interact only with semantically similar ones. Furthermore, CorrCLIP obtains an understanding of an image's semantic layout via self-supervised models to determine concrete similarity values between image patches, which addresses the similarity irregularity problem caused by the aforementioned restricted patch interaction regime. Finally, CorrCLIP reuses the region masks produced by SAM to update the segmentation map. As a training-free method, CorrCLIP achieves a notable improvement across eight challenging benchmarks regarding the averaged mean Intersection over Union, boosting it from 44.4% to 51.0%.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2411.10086")

Code

Syntology Ran 0 of 9 code samples harvested from 1 repository linked to this paper; 9 have no recorded run.

By repository: official repository: 9 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zdk258/CorrCLIP officialmentioned on GitHubpytorch 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; 0 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

9unverified

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zdk258/CorrCLIP. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

gather_features zdk258/CorrCLIP/CorrCLIPv1/open_clip/loss.py official repository unverified no licence file found · pointer only · ddcbd45e940484ee · report
generate_distinct_colors zdk258/CorrCLIP/CorrCLIPv1/demo_colab.py official repository unverified no licence file found · pointer only · 38fc34495256c6cf · report
generate_distinct_colors zdk258/CorrCLIP/CorrCLIPv1/demo_gradio.py official repository unverified no licence file found · pointer only · 8e6ee615153e5dfb · report
get_cls_idx zdk258/CorrCLIP/CorrCLIPv1/corrclip_segmentor.py official repository unverified no licence file found · pointer only · 54731d24b3557840 · report
neighbour_exchange zdk258/CorrCLIP/CorrCLIPv1/open_clip/loss.py official repository unverified no licence file found · pointer only · e332856e3c2fc814 · report
neighbour_exchange_bidir zdk258/CorrCLIP/CorrCLIPv1/open_clip/loss.py official repository unverified no licence file found · pointer only · 5b1fd364afcf3c05 · report
prepare_inputs_for_generation zdk258/CorrCLIP/CorrCLIPv1/open_clip/coca_model.py official repository unverified no licence file found · pointer only · fb651d0a97fd4d3f · report
register_pooler zdk258/CorrCLIP/CorrCLIPv1/open_clip/hf_model.py official repository unverified no licence file found · pointer only · 2a377da4a76a2d44 · report
run_segmentation zdk258/CorrCLIP/CorrCLIPv1/demo_colab.py official repository unverified no licence file found · pointer only · 434ff5d8530045d3 · report

Tasks

Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-trainingZero-Shot Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Semantic Segmentation with Language-image Pre-training ADE20K CorrCLIP Mean IoU (val) 30.7 #1 of 13 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Object CorrCLIP mIoU 49.4 #1 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-171 CorrCLIP mIoU 34.0 #1 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training Cityscapes val CorrCLIP mIoU 51.1 #1 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL Context-59 CorrCLIP mIoU 50.8 #1 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL Context-60 CorrCLIP mIoU 44.9 #1 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL VOC CorrCLIP mIoU 76.7 #1 of 10 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PascalVOC-20 CorrCLIP mIoU 91.8 #1 of 10 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

CLIPDINODense ConnectionsSAMVision Transformer

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