Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples

Abstract

Humans are capable of learning a new fine-grained concept with very little supervision, \emph{e.g.}, few exemplary images for a species of bird, yet our best deep learning systems need hundreds or thousands of labeled examples. In this paper, we try to reduce this gap by studying the fine-grained image recognition problem in a challenging few-shot learning setting, termed few-shot fine-grained recognition (FSFG). The task of FSFG requires the learning systems to build classifiers for novel fine-grained categories from few examples (only one or less than five). To solve this problem, we propose an end-to-end trainable deep network which is inspired by the state-of-the-art fine-grained recognition model and is tailored for the FSFG task. Specifically, our network consists of a bilinear feature learning module and a classifier mapping module: while the former encodes the discriminative information of an exemplar image into a feature vector, the latter maps the intermediate feature into the decision boundary of the novel category. The key novelty of our model is a "piecewise mappings" function in the classifier mapping module, which generates the decision boundary via learning a set of more attainable sub-classifiers in a more parameter-economic way. We learn the exemplar-to-classifier mapping based on an auxiliary dataset in a meta-learning fashion, which is expected to be able to generalize to novel categories. By conducting comprehensive experiments on three fine-grained datasets, we demonstrate that the proposed method achieves superior performance over the competing baselines.

arXiv commentAccepted by IEEE TIP

References in corpus (7)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Learning feed-forward one-shot learners
• Weakly Supervised Fine-Grained Image Categorization
• One-Shot Generalization in Deep Generative Models

Cited by in corpus (17)

• Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment
• TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples
• Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
• Deep Learning for Fine-Grained Image Analysis: A Survey
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition
• Few-shot Classification via Adaptive Attention
• Region Comparison Network for Interpretable Few-shot Image Classification
• Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
• Fine-Grained Image Analysis with Deep Learning: A Survey
• Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View
• NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification
• Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification
• Parametric Contrastive Learning
• Dataset Bias in Few-shot Image Recognition
• ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval