Pith. sign in

REVIEW 4 cited by

Scaling Open-Vocabulary Object Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.09683 v3 pith:TQNX5JZL submitted 2023-06-16 cs.CV

Matthias Minderer , Alexey Gritsenko , Neil Houlsby This is my paper · ORCID
classification cs.CV
keywords detectiontrainingowl-stdataopen-vocabularyself-trainingannotationsbeen
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Open-vocabulary object detection has benefited greatly from pretrained vision-language models, but is still limited by the amount of available detection training data. While detection training data can be expanded by using Web image-text pairs as weak supervision, this has not been done at scales comparable to image-level pretraining. Here, we scale up detection data with self-training, which uses an existing detector to generate pseudo-box annotations on image-text pairs. Major challenges in scaling self-training are the choice of label space, pseudo-annotation filtering, and training efficiency. We present the OWLv2 model and OWL-ST self-training recipe, which address these challenges. OWLv2 surpasses the performance of previous state-of-the-art open-vocabulary detectors already at comparable training scales (~10M examples). However, with OWL-ST, we can scale to over 1B examples, yielding further large improvement: With an L/14 architecture, OWL-ST improves AP on LVIS rare classes, for which the model has seen no human box annotations, from 31.2% to 44.6% (43% relative improvement). OWL-ST unlocks Web-scale training for open-world localization, similar to what has been seen for image classification and language modelling.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LPOI: Listwise Preference Optimization for Vision Language Models

    cs.CV 2025-05 conditional novelty 7.0 of 10

    LPOI reduces VLM hallucination by training the model to prefer the original image over progressively masked versions of the same image, using a listwise ranking loss built from pairwise preference data.

  2. DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection

    cs.CV 2026-03 conditional novelty 6.0 of 10

    Detection Prompt Optimization (DetPO) improves few-shot object detection with black-box MLLMs by iteratively refining text prompts from TP/FP/FN errors on few-shot examples, gaining up to 9.7 mAP over prior black-box methods.

  3. Understanding Trade offs When Conditioning Synthetic Data

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Diverse layout-plus-prompt conditioning of diffusion models generates synthetic data that improves few-shot object detection mAP by up to 177% over real-data-only training, while prompt-only conditioning wins when con...

  4. MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Ten leading VLMs mostly fail to report removed essential object parts as missing, and simulated detector evidence, image tools, longer reasoning, and an easier fine-tune barely improve accuracy.

Pith tools