Papers › Side Adapter Network for Open-Vocabulary Semantic Segmentation

Side Adapter Network for Open-Vocabulary Semantic Segmentation

23 Feb 2023CVPR 2023 1arXiv:2302.12242archive 2025-07-28

Mengde Xu, Zheng Zhang, Fangyun Wei, Han Hu, Xiang Bai

This paper presents a new framework for open-vocabulary semantic segmentation with the pre-trained vision-language model, named Side Adapter Network (SAN). Our approach models the semantic segmentation task as a region recognition problem. A side network is attached to a frozen CLIP model with two branches: one for predicting mask proposals, and the other for predicting attention bias which is applied in the CLIP model to recognize the class of masks. This decoupled design has the benefit CLIP in recognizing the class of mask proposals. Since the attached side network can reuse CLIP features, it can be very light. In addition, the entire network can be trained end-to-end, allowing the side network to be adapted to the frozen CLIP model, which makes the predicted mask proposals CLIP-aware. Our approach is fast, accurate, and only adds a few additional trainable parameters. We evaluate our approach on multiple semantic segmentation benchmarks. Our method significantly outperforms other counterparts, with up to 18 times fewer trainable parameters and 19 times faster inference speed. We hope our approach will serve as a solid baseline and help ease future research in open-vocabulary semantic segmentation. The code will be available at https://github.com/MendelXu/SAN.

PaperPDFConference PDFCodeCode 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="2302.12242")

Code

Syntology Ran 1 of 9 code samples harvested from 2 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 8 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.

mendelxu/san officialmentioned in papermentioned on GitHubpytorchMIT report
blumenstiel/SAN-MESS mentioned on GitHubpytorchMIT report
mendelxu/zsseg.baseline mentioned on GitHubpytorchMIT 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; 1 ran; 0 honoured the contract we drafted; 8 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.

1ran
8unverified

Licence: 0 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

get_predefined_templates mendelxu/san/san/model/clip_utils/utils.py official repository ran MIT (permissive) · c266c766b74bafca · report
batch_dice_loss blumenstiel/SAN-MESS/san/model/matcher.py community (archive-listed) unverified MIT (permissive) · bc2cb481a75c370d · report
batch_sigmoid_ce_loss blumenstiel/SAN-MESS/san/model/matcher.py community (archive-listed) unverified MIT (permissive) · 1edd24985036b0bf · report
calculate_uncertainty blumenstiel/SAN-MESS/san/model/criterion.py community (archive-listed) unverified MIT (permissive) · 2dcb8123d89bb1ff · report
cross_attn_with_self_bias blumenstiel/SAN-MESS/san/model/attn_helper.py community (archive-listed) unverified MIT (permissive) · 629dc217312c9bb7 · report
cross_attn_with_self_bias_func blumenstiel/SAN-MESS/san/model/attn_helper.py community (archive-listed) unverified MIT (permissive) · 920416fe2ccdac57 · report
dice_loss blumenstiel/SAN-MESS/san/model/criterion.py community (archive-listed) unverified MIT (permissive) · 89f75e54ff128be0 · report
get_tiles blumenstiel/SAN-MESS/mess/prepare_datasets/prepare_floodnet.py community (archive-listed) unverified MIT (permissive) · 080cb1a082ca2feb · report
sigmoid_ce_loss blumenstiel/SAN-MESS/san/model/criterion.py community (archive-listed) unverified MIT (permissive) · d0c61e8dba511aa3 · report

Tasks

Language ModellingOpen Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic SegmentationZero Shot Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Semantic Segmentation ADE20K-847 SAN mIoU 13.7 #12 of 19 Archive leaderboard report
Zero Shot Segmentation Segmentation in the Wild SAN Mean AP 41.4 #5 of 12 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

AdapterCLIP

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