CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks
share
Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this potential on a subset of tasks, important questions remain: 1) What is the benefit of CLIP on unstudied VL tasks? 2) Does CLIP provide benefit in low-shot or domain-shifted scenarios? 3) Can CLIP improve existing approaches without impacting inference or pretraining complexity? In this work, we seek to answer these questions through two key contributions. First, we introduce an evaluation protocol that includes Visual Commonsense Reasoning (VCR), Visual Entailment (SNLI-VE), and Visual Question Answering (VQA), across a variety of data availability constraints and conditions of domain shift. Second, we propose an approach, named CLIP Targeted Distillation (CLIP-TD), to intelligently distill knowledge from CLIP into existing architectures using a dynamically weighted objective applied to adaptively selected tokens per instance. Experiments demonstrate that our proposed CLIP-TD leads to exceptional gains in the low-shot (up to 51.9 71.3 standard fully-supervised conditions (up to 2 performance on VCR compared to other single models that are pretrained with image-text data only. On SNLI-VE, CLIP-TD produces significant gains in low-shot conditions (up to 6.6 VQA, CLIP-TD provides improvement in low-shot (up to 9 fully-supervised (up to 1.3 utilizing CLIP for finetuning, as well as baseline naive distillation approaches. Code will be made available.
READ FULL TEXT
