Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models

About

Large pre-trained vision-language (VL) models can learn a new task with a handful of examples and generalize to a new task without fine-tuning. However, these VL models are hard to deploy for real-world applications due to their impractically huge sizes and slow inference speed. To solve this limitation, we study prompt-based low-resource learning of VL tasks with our proposed method, FewVLM, relatively smaller than recent few-shot learners. For FewVLM, we pre-train a sequence-to-sequence transformer model with prefix language modeling (PrefixLM) and masked language modeling (MaskedLM). Furthermore, we analyze the effect of diverse prompts for few-shot tasks. Experimental results on VQA show that FewVLM with prompt-based learning outperforms Frozen which is 31x larger than FewVLM by 18.2% point and achieves comparable results to a 246x larger model, PICa. In our analysis, we observe that (1) prompts significantly affect zero-shot performance but marginally affect few-shot performance, (2) models with noisy prompts learn as quickly as hand-crafted prompts given larger training data, and (3) MaskedLM helps VQA tasks while PrefixLM boosts captioning performance. Our code is publicly available at \url{https://github.com/woojeongjin/FewVLM}

Woojeong Jin, Yu Cheng, Yelong Shen, Weizhu Chen, Xiang Ren• 2021

Related benchmarks

TaskDatasetResultRank
Visual Question AnsweringVQA v2
Accuracy51.1
1165
Visual Question AnsweringGQA
Accuracy35.7
963
Visual Question AnsweringVQA v2 (test-dev)
Overall Accuracy47.7
664
Visual Question AnsweringOK-VQA (test)
Accuracy23.1
296
5-way ClassificationminiImageNet (test)--
231
Visual Question AnsweringGQA (test-dev)
Accuracy29.3
178
Visual Question AnsweringVQAv2
Accuracy47.7
177
Visual Question AnsweringVQA 2.0 (val)
Accuracy (Overall)51.1
143
Image CaptioningFlickr30k (test)
CIDEr37
103
Image CaptioningNoCaps
CIDEr47.7
101
Showing 10 of 19 rows

Other info

Code

Follow for update