Pith. sign in

REVIEW 4 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.08484 v2 pith:QQEJ4SS7 submitted 2021-10-16 cs.CV cs.CL

classification cs.CVcs.CL
keywords fewvlmmodelspromptsfew-shotlargerlearningperformanceprompt-based
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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}

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation

    cs.CV 2025-06 reject novelty 5.0 of 10

    DiMPLe separates CLIP's image and text features into invariant and spurious components and claims large OOD accuracy gains through cross-modal alignment of the invariant parts.

  2. Integrated Structural Prompt Learning for Vision-Language Models

    cs.CV 2025-07 reject novelty 4.0 of 10

    An integrated structural prompt learning method for CLIP reports a state-of-the-art average harmonic mean of 80.70 on 11 base-to-new few-shot classification benchmarks using self- and cross-modal prompt-token interact...

  3. Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection

    cs.CL 2025-05 reject novelty 4.0 of 10

    A hybrid Euclidean-distance and LLM-relevance example selector for few-shot sensor classification reports a small, statistically fragile gain over distance-only selection on a fatigue detection dataset.

  4. Multimodal AI for Gastrointestinal Diagnostics: Tackling VQA in MEDVQA-GI 2025

    cs.CV 2025-07 conditional novelty 3.0 of 10

    Fine-tuning Florence-2 on a 1% subset of Kvasir-VQA with medical image augmentations yields moderate VQA performance on gastrointestinal endoscopy questions.

Pith tools