Learning Primitive-aware Discriminative Representations for Few-shot Learning

TL;DR

This paper introduces a primitive-aware representation learning method for few-shot learning, leveraging primitive mining, reasoning, and a novel metric to improve classification of novel classes with limited samples.

Contribution

It proposes a Primitive Mining and Reasoning Network (PMRN) that incorporates primitive-aware features, a self-supervised Jigsaw task, adaptive clustering, and a graph-based correlation reasoning module for enhanced few-shot learning.

Findings

Achieves state-of-the-art results on six benchmarks.

Outperforms existing methods in accuracy and transferability.

Demonstrates the effectiveness of primitive-aware representations.

Abstract

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to recognize novel classes with only a few labeled examples. Some recent work about FSL has yielded promising classification performance, where the image-level feature is used to calculate the similarity among samples for classification. However, the image-level feature ignores abundant fine-grained and structural in-formation of objects that may be transferable and consistent between seen and unseen classes. How can humans easily identify novel classes with several sam-ples? Some study from cognitive science argues that humans can recognize novel categories through primitives. Although base and novel categories are non-overlapping, they can share some primitives in common. Inspired by above re-search, we propose a Primitive Mining and Reasoning Network (PMRN) to learn primitive-aware representations based on metric-based FSL model. Concretely, we first add Self-supervision Jigsaw task (SSJ) for feature extractor parallelly, guiding the model to encode visual pattern corresponding to object parts into fea-ture channels. To further mine discriminative representations, an Adaptive Chan-nel Grouping (ACG) method is applied to cluster and weight spatially and se-mantically related visual patterns to generate a group of visual primitives. To fur-ther enhance the discriminability and transferability of primitives, we propose a visual primitive Correlation Reasoning Network (CRN) based on graph convolu-tional network to learn abundant structural information and internal correlation among primitives. Finally, a primitive-level metric is conducted for classification in a meta-task based on episodic training strategy. Extensive experiments show that our method achieves state-of-the-art results on six standard benchmarks.