Timezone: »

Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
Yan Zeng · Xinsong Zhang · Hang Li

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #334

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.

Author Information

Yan Zeng (ByteDance AI Lab)
Xinsong Zhang (Bytedance AI Lab)
Hang Li (Bytedance Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors