Few-Shot Image Recognition by Predicting Parameters from Activations

Abstract

In this paper, we are interested in the few-shot learning problem. In particular, we focus on a challenging scenario where the number of categories is large and the number of examples per novel category is very limited, e.g. 1, 2, or 3. Motivated by the close relationship between the parameters and the activations in a neural network associated with the same category, we propose a novel method that can adapt a pre-trained neural network to novel categories by directly predicting the parameters from the activations. Zero training is required in adaptation to novel categories, and fast inference is realized by a single forward pass. We evaluate our method by doing few-shot image recognition on the ImageNet dataset, which achieves the state-of-the-art classification accuracy on novel categories by a significant margin while keeping comparable performance on the large-scale categories. We also test our method on the MiniImageNet dataset and it strongly outperforms the previous state-of-the-art methods.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Densely Connected Convolutional Networks
• Wide Residual Networks
• Matching Networks for One Shot Learning
• What makes ImageNet good for transfer learning?
• Unsupervised Learning of Visual Representations using Videos
• Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
• Transfer of View-manifold Learning to Similarity Perception of Novel Objects
• SORT: Second-Order Response Transform for Visual Recognition

Cited by in corpus (9)

• Meta-Learning with Latent Embedding Optimization
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• Low-Shot Learning with Imprinted Weights
• A Novel BiLevel Paradigm for Image-to-Image Translation
• Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
• Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition
• Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
• Few Shot Learning with Simplex
• On Hard Episodes in Meta-Learning