Skip to yearly menu bar Skip to main content


MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

Jianjian Cao · Peng Ye · Shengze Li · Chong Yu · Yansong Tang · Jiwen Lu · Tao Chen

Arch 4A-E Poster #106
[ ] [ Project Page ]
Thu 20 Jun 5 p.m. PDT — 6:30 p.m. PDT


Vision-Language Transformers (VLTs) have shown great success recently, but are meanwhile accompanied by heavy computation costs, where a major reason can be attributed to the large number of visual and language tokens. Existing token pruning research for compressing VLTs mainly follows a single-modality-based scheme yet ignores the critical role of aligning different modalities for guiding the token pruning process, causing the important tokens for one modality to be falsely pruned in another modality branch. Meanwhile, existing VLT pruning works also lack the flexibility to dynamically compress each layer based on different input samples. To this end, we propose a novel framework named Multimodal Alignment-Guided Dynamic Token Prunning (MADTP) for accelerating various VLTs. Specifically, we first introduce a well-designed Multi-modality Alignment Guidance (MAG) module that can align features of the same semantic concept from different modalities, to ensure the pruned tokens are less important for all modalities. We further design a novel Dynamic Token Pruning (DTP) module, which can adaptively adjust the token compression ratio in each layer based on different input instances. Extensive experiments on various benchmarks demonstrate that MADTP significantly reduces the computational complexity of kinds of multimodal models while preserving competitive performance. Notably, when applied to the BLIP model in the NLVR2 dataset, MADTP can reduce the GFLOPs by 80% with less than 4% performance degradation.

Live content is unavailable. Log in and register to view live content