VIOLA: Towards Video In-Context Learning with Minimal Annotations

TL;DR

VIOLA introduces a label-efficient video in-context learning framework that combines minimal expert annotations with unlabeled data, employing density-based sampling and confidence-aware retrieval to enhance multimodal model adaptation.

Contribution

The paper presents a novel hybrid approach that effectively utilizes minimal annotations and unlabeled data for video domain adaptation in multimodal large language models.

Findings

Significantly outperforms baselines in low-resource settings

Achieves robust adaptation with minimal annotation costs

Demonstrates effectiveness across nine diverse benchmarks

Abstract

Generalizing Multimodal Large Language Models (MLLMs) to novel video domains is essential for real-world deployment but remains challenging due to the scarcity of labeled data. While In-Context Learning (ICL) offers a training-free adaptation path, standard methods rely on large annotated pools, which are often impractical in specialized environments like industrial or surgical settings since they require the experts' annotations. To bridge this gap, we introduce VIOLA (Video In-cOntext Learning with minimal Annotation), a label-efficient framework that synergizes minimal expert supervision with abundant unlabeled data. First, to maximize the efficiency of a strict annotation budget, we propose density-uncertainty-weighted sampling. Unlike standard diversity or uncertainty strategies that risk selecting visual outliers, our method leverages density estimation to identify samples that are simultaneously diverse, representative, and informative. Second, to utilize the remaining unlabeled data without noise propagation, we construct a hybrid pool and introduce confidence-aware retrieval and confidence-aware prompting. These mechanisms explicitly model label reliability, retrieving demonstrations based on a composite score of similarity and confidence while enabling the MLLM to adaptively distinguish between verified ground truths and noisy pseudo-labels. Extensive experiments across nine diverse benchmarks using four MLLMs demonstrate that our framework significantly outperforms various baselines in low-resource settings, achieving robust adaptation with minimal annotation costs.