Papers › Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part...

Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation

16 Jan 2025CVPR 2025 1arXiv:2501.09688archive 2025-07-28

Jiho Choi, Seonho Lee, Minhyun Lee, Seungho Lee, Hyunjung Shim

Open-Vocabulary Part Segmentation (OVPS) is an emerging field for recognizing fine-grained parts in unseen categories. We identify two primary challenges in OVPS: (1) the difficulty in aligning part-level image-text correspondence, and (2) the lack of structural understanding in segmenting object parts. To address these issues, we propose PartCATSeg, a novel framework that integrates object-aware part-level cost aggregation, compositional loss, and structural guidance from DINO. Our approach employs a disentangled cost aggregation strategy that handles object and part-level costs separately, enhancing the precision of part-level segmentation. We also introduce a compositional loss to better capture part-object relationships, compensating for the limited part annotations. Additionally, structural guidance from DINO features improves boundary delineation and inter-part understanding. Extensive experiments on Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets demonstrate that our method significantly outperforms state-of-the-art approaches, setting a new baseline for robust generalization to unseen part categories.

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="2501.09688")

Code

Syntology Ran 7 of 11 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kaist-cvml/part-catseg officialmentioned in papermentioned on GitHubjaxMIT 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

11 samples harvested; 7 ran; 1 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.

1ran · honoured contract
1ran · fixture could not drive it
5ran
4unverified

Licence: 0 of the 11 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 kaist-cvml/part-catseg. “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.

elu_feature_map kaist-cvml/part-catseg/baselines/modeling/transformer/obj_part_cat_seg_model.py official repository ran · honoured contract fingerprinted MIT (permissive) · 0d5505bd782b4a89 · report
infer_metric_tags_from_eval_results kaist-cvml/part-catseg/transformers/modelcard.py official repository ran MIT (permissive) · dd8f7751ef859581 · report
load_imagenet_labels kaist-cvml/part-catseg/datasets/partimagenet_preprocess.py official repository ran MIT (permissive) · 26175e73e7041e86 · report
parse_keras_history kaist-cvml/part-catseg/transformers/modelcard.py official repository ran MIT (permissive) · a4491b45d19b7a39 · report
preprocess_partimagenet kaist-cvml/part-catseg/datasets/partimagenet_preprocess.py official repository ran MIT (permissive) · ee588a4e50fa1acd · report
window_partition kaist-cvml/part-catseg/baselines/modeling/transformer/obj_part_cat_seg_model.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 993ae96666b00cb5 · report
window_reverse kaist-cvml/part-catseg/baselines/modeling/transformer/obj_part_cat_seg_model.py official repository ran MIT (permissive) · 265c72d3ccc64544 · report
check_imports kaist-cvml/part-catseg/transformers/dynamic_module_utils.py official repository unverified MIT (permissive) · f4075cdecbb730c5 · report
get_relative_import_files kaist-cvml/part-catseg/transformers/dynamic_module_utils.py official repository unverified MIT (permissive) · 00cc853a73f3aeb6 · report
get_relative_imports kaist-cvml/part-catseg/transformers/dynamic_module_utils.py official repository unverified MIT (permissive) · 450aeffe7f80f917 · report
is_hf_dataset kaist-cvml/part-catseg/transformers/modelcard.py official repository unverified MIT (permissive) · ec7b1528a936234d · report

Tasks

Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDINODense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision 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