Learning Object-Language Alignments for Open-Vocabulary Object Detection

by   Chuang Lin, et al.
Monash University

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an attractive alternative for its annotation-free attributes and broader object concepts. However, learning open-vocabulary object detection from language is challenging since image-text pairs do not contain fine-grained object-language alignments. Previous solutions rely on either expensive grounding annotations or distilling classification-oriented vision models. In this paper, we propose a novel open-vocabulary object detection framework directly learning from image-text pair data. We formulate object-language alignment as a set matching problem between a set of image region features and a set of word embeddings. It enables us to train an open-vocabulary object detector on image-text pairs in a much simple and effective way. Extensive experiments on two benchmark datasets, COCO and LVIS, demonstrate our superior performance over the competing approaches on novel categories, e.g. achieving 32.0 mAP on LVIS. Code is available at: https://github.com/clin1223/VLDet.


page 2

page 7

page 15


RegionCLIP: Region-based Language-Image Pretraining

Contrastive language-image pretraining (CLIP) using image-text pairs has...

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment

This paper presents DetCLIPv2, an efficient and scalable training framew...

Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model

Recently, vision-language pre-training shows great potential in open-voc...

Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization

Open-vocabulary object detection (OVD) aims to scale up vocabulary size ...

Aligning Bag of Regions for Open-Vocabulary Object Detection

Pre-trained vision-language models (VLMs) learn to align vision and lang...

Going Denser with Open-Vocabulary Part Segmentation

Object detection has been expanded from a limited number of categories t...

Open-vocabulary Attribute Detection

Vision-language modeling has enabled open-vocabulary tasks where predict...

Please sign up or login with your details

Forgot password? Click here to reset