Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
Most existing methods in vision language pre-training rely on object-centric features extracted through object detection and make fine-grained alignments between the extracted features and texts. It is challenging for these methods to learn relations among multiple objects. To this end, we propose a new method called X-VLM to perform `multi-grained vision language pre-training.' The key to learning multi-grained alignments is to locate visual concepts in the image given the associated texts, and in the meantime align the texts with the visual concepts, where the alignments are in multi-granularity. Experimental results show that X-VLM effectively leverages the learned multi-grained alignments to many downstream vision language tasks and consistently outperforms state-of-the-art methods.
PDF AbstractCode
MS COCO
Visual Genome
Flickr30k
Visual Question Answering v2.0
RefCOCO
COCO Captions
Objects365
CC12M
NLVR
OVAD benchmark
Results from the Paper
Ranked #1 on
Image Retrieval
on Flickr30K 1K test
(using extra training data)
