FILIP: Fine-grained Interactive Language-Image Pre-Training

TL;DR

FILIP introduces a scalable, efficient fine-grained cross-modal pre-training method that improves alignment between image patches and textual words, achieving state-of-the-art results on vision-language tasks.

Contribution

The paper proposes a novel late interaction mechanism for fine-grained alignment in vision-language pre-training, enabling efficient offline representation computation.

Findings

FILIP achieves state-of-the-art performance on multiple downstream tasks.

The method effectively learns meaningful fine-grained features and localization.

FILIP's approach maintains efficiency in large-scale training and inference.

Abstract

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which misses sufficient information, or finer-grained interactions using cross/self-attention upon visual and textual tokens. However, cross/self-attention suffers from inferior efficiency in both training and inference. In this paper, we introduce a large-scale Fine-grained Interactive Language-Image Pre-training (FILIP) to achieve finer-level alignment through a cross-modal late interaction mechanism, which uses a token-wise maximum similarity between visual and textual tokens to guide the contrastive objective. FILIP successfully leverages the finer-grained expressiveness between image patches and textual words by modifying only contrastive loss, while simultaneously gaining the ability to pre-compute image and text representations offline at inference, keeping both large-scale training and inference efficient. Furthermore, we construct a new large-scale image-text pair dataset called FILIP300M for pre-training. Experiments show that FILIP achieves state-of-the-art performance on multiple downstream vision-language tasks including zero-shot image classification and image-text retrieval. The visualization on word-patch alignment further shows that FILIP can learn meaningful fine-grained features with promising localization ability.