Year: 2021
Type: conference-paper
Abstract: We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective. Our method lever-ages relational patterns within and between images via self-correlational representation (SCR) and cross-correlational attention (CCA). Within each image, the SCR module transforms a base feature map into a self-correlation tensor and learns to extract structural patterns from the tensor. Between the images, the CCA module computes cross-correlation between two image representations and learns to produce co-attention between them. Our Relational Embedding Network (RENet) combines the two relational modules to learn relational embedding in an end-to-end manner. In experimental evaluation, it achieves consistent improvements over state-of-the-art methods on four widely used few-shot classification benchmarks of miniImageNet, tieredImageNet, CUB-200-2011, and CIFAR-FS.
Authors: Dahyun Kang, Heeseung Kwon, Juhong Min, Minsu Cho
Institution: Pohang University of Science and Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3193823652
