`

Timezone: »

Poster
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
Junnan Li · Ramprasaath Selvaraju · Akhilesh Gotmare · Shafiq Joty · Caiming Xiong · Steven Chu Hong Hoi

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @ None #None
Large-scale vision and language representation learning has shown promising improvements on various vision-language tasks. Most existing methods employ a transformer-based multimodal encoder to jointly model visual tokens (region-based image features) and word tokens. Because the visual tokens and word tokens are unaligned, it is challenging for the multimodal encoder to learn image-text interactions. In this paper, we introduce a contrastive loss to ALign the image and text representations BEfore Fusing (ALBEF) them through cross-modal attention, which enables more grounded vision and language representation learning. Unlike most existing methods, our method does not require bounding box annotations nor high-resolution images. In order to improve learning from noisy web data, we propose momentum distillation, a self-training method which learns from pseudo-targets produced by a momentum model. We provide a theoretical analysis of ALBEF from a mutual information maximization perspective, showing that different training tasks can be interpreted as different ways to generate views for an image-text pair. ALBEF achieves state-of-the-art performance on multiple downstream vision-language tasks. On image-text retrieval, ALBEF outperforms methods that are pre-trained on orders of magnitude larger datasets. On VQA and NLVR$^2$, ALBEF achieves absolute improvements of 2.37% and 3.84% compared to the state-of-the-art, while enjoying faster inference speed. Code and models are available at https://github.com/salesforce/ALBEF.

#### Author Information

##### Akhilesh Gotmare (Salesforce Research)

I am a Machine Learning Researcher with Salesforce Research Asia in Singapore. I finished my MSc at the Department of Computer Science at EPFL, Switzerland, where I was working with Prof. Martin Jaggi's Machine Learning and Optimization laboratory for my thesis project. During my Master's, I was an intern with Salesforce Research in Palo Alto (Apr - Sept 2018).