Papers › CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

2 Oct 2023arXiv:2310.01403archive 2025-07-28

Size Wu, Wenwei Zhang, Lumin Xu, Sheng Jin, Xiangtai Li, Wentao Liu, Chen Change Loy

Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers (ViTs), have exhibited remarkable generalization ability in zero-shot image classification. However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions. In this paper, we embark on an in-depth analysis of the region-language alignment in CLIP models, which is essential for downstream open-vocabulary dense prediction tasks. Subsequently, we propose an approach named CLIPSelf, which adapts the image-level recognition ability of CLIP ViT to local image regions without needing any region-text pairs. CLIPSelf empowers ViTs to distill itself by aligning a region representation extracted from its dense feature map with the image-level representation of the corresponding image crop. With the enhanced CLIP ViTs, we achieve new state-of-the-art performance on open-vocabulary object detection, semantic segmentation, and panoptic segmentation across various benchmarks. Models and code are released at https://github.com/wusize/CLIPSelf.

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="2310.01403")

Code

Syntology Ran 2 of 6 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wusize/clipself officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

6 samples harvested; 2 ran; 0 honoured the contract we drafted; 4 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.

2ran
4unverified

Licence: 6 of the 6 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 wusize/clipself. “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.

load_class_freq wusize/clipself/F-ViT/models/custom_losses.py official repository ran licence not identified · pointer only · 42264faf65871374 · report
load_state_dict wusize/clipself/src/open_clip/factory.py official repository ran no licence file found · pointer only · 4b3a4d17e1df3140 · report
gather_features wusize/clipself/src/open_clip/loss.py official repository unverified licence not identified · pointer only · fd6321f5fd69ea0a · report
get_model_config wusize/clipself/src/open_clip/factory.py official repository unverified no licence file found · pointer only · 5c7cf820e99443ff · report
prepare_inputs_for_generation wusize/clipself/src/open_clip/coca_model.py official repository unverified no licence file found · pointer only · fb651d0a97fd4d3f · report
register_pooler wusize/clipself/src/open_clip/hf_model.py official repository unverified no licence file found · pointer only · 2a377da4a76a2d44 · report

Tasks

Image ClassificationImage SegmentationObject DetectionOpen Vocabulary Object DetectionOpen Vocabulary Panoptic SegmentationOpen Vocabulary Semantic SegmentationOpen-vocabulary object detectionPanoptic SegmentationPredictionSegmentationSemantic SegmentationZero-Shot Image Classificationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Object Detection LVIS v1.0 CLIPSelf AP novel-LVIS base training 34.9 #5 of 28 Archive leaderboard report
Open Vocabulary Object Detection MSCOCO CLIPSelf AP 0.5 44.3 #7 of 32 Archive leaderboard report
Open Vocabulary Panoptic Segmentation ADE20K CLIPSelf PQ 23.7 #6 of 10 Archive leaderboard report
Open Vocabulary Semantic Segmentation ADE20K-150 CLIPSelf mIoU 34.5 #10 of 23 Archive leaderboard report
Open Vocabulary Semantic Segmentation ADE20K-847 CLIPSelf mIoU 12.4 #14 of 19 Archive leaderboard report
Open Vocabulary Semantic Segmentation PASCAL Context-59 CLIPSelf mIoU 62.3 #5 of 24 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

CLIP

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