paper-with-me

홈 › Papers

Scaling Open-Vocabulary Object Detection

2023-06-16 · NeurIPS 2023 11 · Matthias Minderer, Alexey Gritsenko, Neil Houlsby

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.

📄 PDF Abstract BibTeX arXiv:2306.09683

Code (3)

google-research/scenic/tree/main/scenic/projects/owl_vit 공식 구현 jax
MindCode-4/code-2/tree/main/owlvit mindspore
yangyucheng000/University/tree/main/model-1/owlv2 mindspore

Tasks

image-classificationImage ClassificationLanguage ModellingObjectobject-detectionObject DetectionOpen-vocabulary object detectionOpen Vocabulary Object DetectionZero-Shot Object Detection

Similar Papers 제목 키워드 기반

Simple Open-Vocabulary Object Detection with Vision Transformers

2022-05-12 · Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann 외

Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the…

Described Object Detectionimage-classificationImage ClassificationObject+4

F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models

2022-09-30 · Weicheng Kuo, Yin Cui, Xiuye Gu, AJ Piergiovanni 외

We present F-VLM, a simple open-vocabulary object detection method built upon Frozen Vision and Language Models. F-VLM simplifies the current multi-stage training pipeline by eliminating the need for knowledge distillati…

Knowledge Distillationobject-detectionObject DetectionOpen-vocabulary object detection+1

OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network

2022-09-10 · Tiancheng Zhao, Peng Liu, Kyusong Lee

The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an in…

Continual LearningObjectObject DetectionOpen Vocabulary Object Detection+1

Scaling Open-Vocabulary Action Detection

2025-04-04 · Zhen Hao Sia, Yogesh Singh Rawat

In this work, we focus on scaling open-vocabulary action detection. Existing approaches for action detection are predominantly limited to closed-set scenarios and rely on complex, parameter-heavy architectures. Extending…

Action DetectionMultiple Action DetectionOpen Vocabulary Action DetectionSpatio-Temporal Action Localization+2

CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

2023-10-25 · NeurIPS 2023 11 · Chuofan Ma, Yi Jiang, Xin Wen, Zehuan Yuan 외

Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self…

Objectobject-detectionObject DetectionObject Discovery+3