Dense Classification and Implanting for Few-Shot Learning

2019/03/12 by Lifchitz, Yann, Avrithis, Yannis, Picard, Sylvaine +1 · 4 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1903.05050

Abstract

Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks. In this context, we are targeting knowledge transfer from a set with abundant data to other sets with few available examples. We propose two simple and effective solutions: (i) dense classification over feature maps, which for the first time studies local activations in the domain of few-shot learning, and (ii) implanting, that is, attaching new neurons to a previously trained network to learn new, task-specific features. On miniImageNet, we improve the prior state-of-the-art on few-shot classification, i.e., we achieve 62.5%, 79.8% and 83.8% on 5-way 1-shot, 5-shot and 10-shot settings respectively.

Cited by

• CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspective
• A²M²-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition
• Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
• Reliable Few-shot Learning under Dual Noises

Related

• Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
• Few-Shot Image Recognition by Predicting Parameters from Activations
• Continual Local Replacement for Few-shot Learning
• Collaboration of Pre-trained Models Makes Better Few-shot Learner
• Learning from Few Samples: A Survey