One-Shot Open Affordance Learning with Foundation Models

TL;DR

This paper presents a one-shot learning framework for affordance detection using foundation models, achieving high performance with minimal data and demonstrating strong generalization to unseen objects and affordances.

Contribution

It introduces a novel one-shot affordance learning method leveraging vision-language models, enhancing data efficiency and generalization in affordance segmentation.

Findings

Outperforms state-of-the-art models with less than 1% training data

Shows strong generalization to unseen objects and affordances

Effective alignment of visual features and affordance text embeddings

Abstract

We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel objects and affordances. While vision-language models excel at recognizing novel objects and scenes, they often struggle to understand finer levels of granularity such as affordances. To handle this issue, we conduct a comprehensive analysis of existing foundation models, to explore their inherent understanding of affordances and assess the potential for data-limited affordance learning. We then propose a vision-language framework with simple and effective designs that boost the alignment between visual features and affordance text embeddings. Experiments on two affordance segmentation benchmarks show that the proposed method outperforms state-of-the-art models with less than 1% of the full training data, and exhibits reasonable generalization capability on unseen objects and affordances.