Papers › A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for...

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

16 Oct 2021ACL 2022 5arXiv:2110.08484archive 2025-07-28

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

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}

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

woojeongjin/fewvlm officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image CaptioningLanguage ModelingLanguage ModellingMasked Language ModelingVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning Flickr30k Captions test FewVLM CIDEr 31.0 #6 of 7 Archive leaderboard report
Image Captioning Flickr30k Captions test FewVLM SPICE 10.0 #6 of 7 Archive leaderboard report
Visual Question Answering (VQA) GQA test-dev FewVLM (zero-shot) Accuracy 29.3 #17 of 17 Archive leaderboard report
Visual Question Answering (VQA) OK-VQA FewVLM Accuracy 16.5 #34 of 37 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 val Few VLM (zero-shot) Accuracy 47.7 #8 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections