Papers › Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers

Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers

11 May 2023CVPR 2023 1arXiv:2305.07011archive 2025-07-28

Dahun Kim, Anelia Angelova, Weicheng Kuo

We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we propose to randomly crop and resize regions of positional embeddings instead of using the whole image positional embeddings. This better matches the use of positional embeddings at region-level in the detection finetuning phase. In addition, we replace the common softmax cross entropy loss in contrastive learning with focal loss to better learn the informative yet difficult examples. Finally, we leverage recent advances in novel object proposals to improve open-vocabulary detection finetuning. We evaluate our full model on the LVIS and COCO open-vocabulary detection benchmarks and zero-shot transfer. RO-ViT achieves a state-of-the-art 34.1 APᵣ on LVIS, surpassing the best existing approach by +7.8 points in addition to competitive zero-shot transfer detection. Surprisingly, RO-ViT improves the image-level representation as well and achieves the state of the art on 9 out of 12 metrics on COCO and Flickr image-text retrieval benchmarks, outperforming competitive approaches with larger models.

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="2305.07011")

Code

Syntology Ran 5 of 8 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mcahny/rovit officialmentioned in papermentioned on GitHubjax 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

8 samples harvested; 5 ran; 1 honoured the contract we drafted; 3 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
3ran
3unverified

Licence: 0 of the 8 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 google-research/google-research. “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.

Encoder google-research/google-research/moe_mtl/modeling/vit.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d8ad1a5da80c6c5a · report
Encoder1DBlock google-research/google-research/moe_mtl/modeling/vit.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · e2cdd60f8bf0cc83 · report
MlpBlock google-research/google-research/moe_mtl/modeling/vit.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 6d80bcd9c94bd100 · report
get_posemb google-research/google-research/moe_mtl/modeling/vit.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · a8f77cb87a6eb75b · report
posemb_sincos_2d google-research/google-research/moe_mtl/modeling/vit.py official repository ran · honoured contract Apache-2.0 (permissive) · 2d67a8a756fe7cf8 · report
Model google-research/google-research/moe_mtl/modeling/vit.py official repository unverified Apache-2.0 (permissive) · 6aec67ee501d1501 · report
window_merge google-research/google-research/moe_mtl/modeling/vit.py official repository unverified Apache-2.0 (permissive) · 6c0a4f49af0bfb40 · report
window_partition google-research/google-research/moe_mtl/modeling/vit.py official repository unverified Apache-2.0 (permissive) · 476400e99387d750 · report

Tasks

Contrastive LearningImage-text RetrievalObject DetectionOpen Vocabulary Object DetectionOpen-vocabulary object detectionRetrievalText RetrievalZero-Shot Cross-Modal Retrievalobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Object Detection LVIS v1.0 RO-ViT AP novel-LVIS base training 32.1 #10 of 28 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 RO-ViT Image-to-text R@1 68.9 #6 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 RO-ViT Image-to-text R@10 92.2 #6 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 RO-ViT Image-to-text R@5 87.8 #6 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 RO-ViT Text-to-image R@1 51.8 #6 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 RO-ViT Text-to-image R@10 83.0 #6 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 RO-ViT Text-to-image R@5 75.0 #6 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k RO-ViT Image-to-text R@1 92.1 #6 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k RO-ViT Image-to-text R@10 99.7 #6 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k RO-ViT Image-to-text R@5 99.4 #6 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k RO-ViT Text-to-image R@1 80.7 #6 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k RO-ViT Text-to-image R@10 97.7 #6 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k RO-ViT Text-to-image R@5 96.1 #6 of 22 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

Contrastive LearningFocal LossSoftmax

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