Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning

Abstract

Object recognition in the real-world requires handling long-tailed or even open-ended data. An ideal visual system needs to recognize the populated head visual concepts reliably and meanwhile efficiently learn about emerging new tail categories with a few training instances. Class-balanced many-shot learning and few-shot learning tackle one side of this problem, by either learning strong classifiers for head or learning to learn few-shot classifiers for the tail. In this paper, we investigate the problem of generalized few-shot learning (GFSL) -- a model during the deployment is required to learn about tail categories with few shots and simultaneously classify the head classes. We propose the ClAssifier SynThesis LEarning (CASTLE), a learning framework that learns how to synthesize calibrated few-shot classifiers in addition to the multi-class classifiers of head classes with a shared neural dictionary, shedding light upon the inductive GFSL. Furthermore, we propose an adaptive version of CASTLE (ACASTLE) that adapts the head classifiers conditioned on the incoming tail training examples, yielding a framework that allows effective backward knowledge transfer. As a consequence, ACASTLE can handle GFSL with classes from heterogeneous domains effectively. CASTLE and ACASTLE demonstrate superior performances than existing GFSL algorithms and strong baselines on MiniImageNet as well as TieredImageNet datasets. More interestingly, they outperform previous state-of-the-art methods when evaluated with standard few-shot learning criteria.

Accepted by IJCV; The code is available at https://github.com/Sha-Lab/aCASTLE

References in corpus (14)

• Distilling the Knowledge in a Neural Network
• On Calibration of Modern Neural Networks
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• On First-Order Meta-Learning Algorithms
• DropBlock: A regularization method for convolutional networks
• Layer Normalization
• SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
• TADAM: Task dependent adaptive metric for improved few-shot learning
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
• Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
• Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
• Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning
• Toward Multimodal Model-Agnostic Meta-Learning

Cited by in corpus (6)

• CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
• Few-Shot Incremental Learning with Continually Evolved Classifiers
• Imbalanced Continual Learning with Partitioning Reservoir Sampling
• Learning Placeholders for Open-Set Recognition
• Unsupervised Transfer Learning with Self-Supervised Remedy
• End-to-end One-shot Human Parsing