LGAICLCVMMJul 9, 2023

FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?

arXiv:2307.04114v13 citationsh-index: 35
Originality Highly original
AI Analysis

This work addresses the challenge of leveraging semantic information from class names in few-shot learning, offering a novel approach that enhances generalization for computer vision tasks.

The paper tackles few-shot image classification by proposing a new framework that integrates pre-trained language models through contrastive learning, achieving state-of-the-art results on multiple benchmarks with improved accuracy.

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However, these works focus on improving existing modules such as visual prototypes and feature extractors of the standard few-shot learning framework. This limits the full potential use of semantic information. In this paper, we propose a novel few-shot learning framework that uses pre-trained language models based on contrastive learning. To address the challenge of alignment between visual features and textual embeddings obtained from text-based pre-trained language model, we carefully design the textual branch of our framework and introduce a metric module to generalize the cosine similarity. For better transferability, we let the metric module adapt to different few-shot tasks and adopt MAML to train the model via bi-level optimization. Moreover, we conduct extensive experiments on multiple benchmarks to demonstrate the effectiveness of our method.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes