Papers › Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

5 Feb 2024arXiv:2402.03094archive 2025-07-28

Yuqian Fu, Yu Wang, Yixuan Pan, Lian Huai, Xingyu Qiu, Zeyu Shangguan, Tong Liu, Yanwei Fu, Luc van Gool, Xingqun Jiang

This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples. While transformer-based open-set detectors, such as DE-ViT, show promise in traditional few-shot object detection, their generalization to CD-FSOD remains unclear: 1) can such open-set detection methods easily generalize to CD-FSOD? 2) If not, how can models be enhanced when facing huge domain gaps? To answer the first question, we employ measures including style, inter-class variance (ICV), and indefinable boundaries (IB) to understand the domain gap. Based on these measures, we establish a new benchmark named CD-FSOD to evaluate object detection methods, revealing that most of the current approaches fail to generalize across domains. Technically, we observe that the performance decline is associated with our proposed measures: style, ICV, and IB. Consequently, we propose several novel modules to address these issues. First, the learnable instance features align initial fixed instances with target categories, enhancing feature distinctiveness. Second, the instance reweighting module assigns higher importance to high-quality instances with slight IB. Third, the domain prompter encourages features resilient to different styles by synthesizing imaginary domains without altering semantic contents. These techniques collectively contribute to the development of the Cross-Domain Vision Transformer for CD-FSOD (CD-ViTO), significantly improving upon the base DE-ViT. Experimental results validate the efficacy of our model.

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="2402.03094")

Code

Syntology Ran 9 of 11 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 9 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lovelyqian/CDFSOD-benchmark officialmentioned on GitHubpytorchApache-2.0 report
LONGXUANX/CDFormer_code mentioned 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

11 samples harvested; 9 ran; 0 honoured the contract we drafted; 2 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.

9ran
2unverified

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 lovelyqian/CDFSOD-benchmark. “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.

box_cxcywh_to_xyxy lovelyqian/CDFSOD-benchmark/lib/regionprop.py official repository ran fingerprinted Apache-2.0 (permissive) · 009912c75c8c77cf · report
box_xyxy_clamp lovelyqian/CDFSOD-benchmark/lib/regionprop.py official repository ran fingerprinted Apache-2.0 (permissive) · 88d32e10c27e7a12 · report
box_xyxy_to_cxcywh lovelyqian/CDFSOD-benchmark/lib/regionprop.py official repository ran fingerprinted Apache-2.0 (permissive) · db78cfc20095f3a8 · report
convert_basic_c2_names lovelyqian/CDFSOD-benchmark/detectron2/checkpoint/c2_model_loading.py official repository ran Apache-2.0 (permissive) · e8526a516b4f9206 · report
convert_basic_clip_names lovelyqian/CDFSOD-benchmark/detectron2/checkpoint/clip_model_loading.py official repository ran Apache-2.0 (permissive) · 7b7f6e4aa28b1a69 · report
convert_c2_detectron_names lovelyqian/CDFSOD-benchmark/detectron2/checkpoint/c2_model_loading.py official repository ran Apache-2.0 (permissive) · e36f87059208bb7e · report
convert_clip_names lovelyqian/CDFSOD-benchmark/detectron2/checkpoint/clip_model_loading.py official repository ran Apache-2.0 (permissive) · 376248f5d186a885 · report
mask_sinkhorn lovelyqian/CDFSOD-benchmark/lib/prototype_learner.py official repository ran Apache-2.0 (permissive) · 9d4bd1f443b65407 · report
sinkhorn lovelyqian/CDFSOD-benchmark/lib/prototype_learner.py official repository ran Apache-2.0 (permissive) · f8c7f9605872c11b · report
align_and_update_state_dicts lovelyqian/CDFSOD-benchmark/detectron2/checkpoint/c2_model_loading.py official repository unverified Apache-2.0 (permissive) · ac2638463572c152 · report
align_and_update_state_dicts_for_CLIP lovelyqian/CDFSOD-benchmark/detectron2/checkpoint/clip_model_loading.py official repository unverified Apache-2.0 (permissive) · 0bd7b0a60b4069f9 · report

Tasks

Cross-Domain Few-ShotCross-Domain Few-Shot Object DetectionFew-Shot Object DetectionObjectObject DetectionOpen Vocabulary Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Domain Few-Shot Object Detection Artaxor CD-ViTO mAP 60.5 #3 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Clipark1k CD-ViTO mAP 44.3 #4 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR CD-ViTO mAP 30.8 #4 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DeepFish CD-ViTO mAP 22.3 #5 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection NEU-DET CD-ViTO mAP 12.8 #5 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD CD-ViTO mAP 7.0 #13 of 16 Archive leaderboard report
Few-Shot Object Detection MS-COCO (10-shot) CD-ViTO AP 35.3 #2 of 33 Archive leaderboard report
Few-Shot Object Detection MS-COCO (30-shot) CD-ViTO AP 35.9 #2 of 25 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

ALIGNAbsolute Position EncodingsAdamAttentionBASEBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision 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