Variational Feature Disentangling for Fine-Grained Few-Shot Classification

Abstract

Fine-grained few-shot recognition often suffers from the problem of training data scarcity for novel categories.The network tends to overfit and does not generalize well to unseen classes due to insufficient training data. Many methods have been proposed to synthesize additional data to support the training. In this paper, we focus one enlarging the intra-class variance of the unseen class to improve few-shot classification performance. We assume that the distribution of intra-class variance generalizes across the base class and the novel class. Thus, the intra-class variance of the base set can be transferred to the novel set for feature augmentation. Specifically, we first model the distribution of intra-class variance on the base set via variational inference. Then the learned distribution is transferred to the novel set to generate additional features, which are used together with the original ones to train a classifier. Experimental results show a significant boost over the state-of-the-art methods on the challenging fine-grained few-shot image classification benchmarks.

arXiv commentAccepted to ICCV 2021

References in corpus (12)

• Auto-Encoding Variational Bayes
• Prototypical Networks for Few-shot Learning
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Delta-encoder: an effective sample synthesis method for few-shot object recognition
• Understanding disentangling in $\beta$-VAE
• Meta-Learning with Implicit Gradients
• Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
• A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
• Physics-based Shadow Image Decomposition for Shadow Removal
• Adapted Deep Embeddings: A Synthesis of Methods for $k$-Shot Inductive Transfer Learning
• Learning Disentangled Representation for Robust Person Re-identification
• Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition