Papers › ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

9 Aug 2024arXiv:2408.04883archive 2025-07-28

Mengcheng Lan, Chaofeng Chen, Yiping Ke, Xinjiang Wang, Litong Feng, Wayne Zhang

Open-vocabulary semantic segmentation requires models to effectively integrate visual representations with open-vocabulary semantic labels. While Contrastive Language-Image Pre-training (CLIP) models shine in recognizing visual concepts from text, they often struggle with segment coherence due to their limited localization ability. In contrast, Vision Foundation Models (VFMs) excel at acquiring spatially consistent local visual representations, yet they fall short in semantic understanding. This paper introduces ProxyCLIP, an innovative framework designed to harmonize the strengths of both CLIP and VFMs, facilitating enhanced open-vocabulary semantic segmentation. ProxyCLIP leverages the spatial feature correspondence from VFMs as a form of proxy attention to augment CLIP, thereby inheriting the VFMs' robust local consistency and maintaining CLIP's exceptional zero-shot transfer capacity. We propose an adaptive normalization and masking strategy to get the proxy attention from VFMs, allowing for adaptation across different VFMs. Remarkably, as a training-free approach, ProxyCLIP significantly improves the average mean Intersection over Union (mIoU) across eight benchmarks from 40.3 to 44.4, showcasing its exceptional efficacy in bridging the gap between spatial precision and semantic richness for the open-vocabulary segmentation task.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2408.04883")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · our draft was wrong.

By repository: official repository: 9 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mc-lan/proxyclip officialmentioned in papermentioned 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; 3 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
6unverified

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 mc-lan/proxyclip. “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.

convert_to_custom_text_state_dict mc-lan/proxyclip/open_clip/model.py official repository ran · violated contract no licence file found · pointer only · f19962ebb134b3d7 · report
get_cast_dtype mc-lan/proxyclip/open_clip/model.py official repository ran · our draft was wrong no licence file found · pointer only · dcd422d66b0581d8 · report
get_input_dtype mc-lan/proxyclip/open_clip/model.py official repository ran · our draft was wrong no licence file found · pointer only · b476c8cfbf0f1f47 · report
gather_features mc-lan/proxyclip/open_clip/loss.py official repository unverified no licence file found · pointer only · ddcbd45e940484ee · report
get_cls_idx mc-lan/proxyclip/proxyclip_segmentor.py official repository unverified no licence file found · pointer only · 54731d24b3557840 · report
neighbour_exchange mc-lan/proxyclip/open_clip/loss.py official repository unverified no licence file found · pointer only · e332856e3c2fc814 · report
neighbour_exchange_bidir mc-lan/proxyclip/open_clip/loss.py official repository unverified no licence file found · pointer only · 5b1fd364afcf3c05 · report
prepare_inputs_for_generation mc-lan/proxyclip/open_clip/coca_model.py official repository unverified no licence file found · pointer only · fb651d0a97fd4d3f · report
register_pooler mc-lan/proxyclip/open_clip/hf_model.py official repository unverified no licence file found · pointer only · 2a377da4a76a2d44 · report

Tasks

Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-training

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Semantic Segmentation with Language-image Pre-training ADE20K ProxyCLIP Mean IoU (val) 24.2 #4 of 13 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Object ProxyCLIP mIoU 39.2 #3 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-171 ProxyCLIP mIoU 26.8 #4 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training Cityscapes val ProxyCLIP mIoU 42.0 #3 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL Context-59 ProxyCLIP mIoU 39.6 #4 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL Context-60 ProxyCLIP mIoU 35.4 #4 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL VOC ProxyCLIP mIoU 65.0 #5 of 10 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PascalVOC-20 ProxyCLIP mIoU 83.3 #5 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

AttentionCLIPSoftmax

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