Log In Sign Up

Learning Primitive-aware Discriminative Representations for FSL

by   Jianpeng Yang, et al.

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to recognize novel classes,given only a few labeled examples per class.Limited data keep this task challenging for deep learning.Recent metric-based methods has achieved promising performance based on image-level features.However,these global features ignore abundant local and structural information that is transferable and consistent between seen and unseen classes.Some study in cognitive science argue that humans can recognize novel classes with the learned primitives.We expect to mine both transferable and discriminative representation from base classes and adopt them to recognize novel classes.Building on the episodic training mechanism,We propose a Primitive Mining and Reasoning Network(PMRN) to learn primitive-aware representation in an end-to-end manner for metric-based FSL model.We first add self-supervision auxiliary task,forcing feature extractor to learn tvisual pattern corresponding to primitives.To further mine and produce transferable primitive-aware representations,we design an Adaptive Channel Grouping(ACG)module to synthesize a set of visual primitives from object embedding by enhancing informative channel maps while suppressing useless ones. Based on the learned primitive feature,a Semantic Correlation Reasoning (SCR) module is proposed to capture internal relations among them.Finally,we learn the task-specific importance of primitives and conduct primitive-level metric based on the task-specific attention feature.Extensive experiments show that our method achieves state-of-the-art results on six standard benchmarks.


page 1

page 2

page 3

page 4


Compositional Few-Shot Recognition with Primitive Discovery and Enhancing

Few-shot learning (FSL) aims at recognizing novel classes given only few...

Towards a self-organizing pre-symbolic neural model representing sensorimotor primitives

The acquisition of symbolic and linguistic representations of sensorimot...

Single Image 3D Object Estimation with Primitive Graph Networks

Reconstructing 3D object from a single image (RGB or depth) is a fundame...

HPNet: Deep Primitive Segmentation Using Hybrid Representations

This paper introduces HPNet, a novel deep-learning approach for segmenti...

ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

Recently, the transductive graph-based methods have achieved great succe...

Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition

This paper proposes a novel model for recognizing images with composite ...

End-to-end One-shot Human Parsing

Previous human parsing models are limited to parsing humans into pre-def...