2019 · 251 citations · 30 references
ComputingComputer ScienceComputer VisionMachine LearningVisual PerceptionDeep LearningImage ClassificationMeta-learningObject RecognitionRepresentation LearningScene UnderstandingBenchmark DatasetsClassifier FusionOne-shot LearningSemantic Information
Humans can robustly learn novel visual concepts even when images undergo various deformations and loose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems perform better one-shot learning, i.e., learning concepts from one or few examples. Our key insight is that, while the deformed images may not be visually realistic, they still maintain critical semantic information and contribute significantly to formulating classifier decision boundaries. Inspired by the recent progress of meta-learning, we combine a meta-learner with an image deformation sub-network that produces additional training examples, and optimize both models in an end-to-end manner. The deformation sub-network learns to deform images by fusing a pair of images --- a probe image that keeps the visual content and a gallery image that diversifies the deformations. We demonstrate results on the widely used one-shot learning benchmarks (miniImageNet and ImageNet 1K Challenge datasets), which significantly outperform state-of-the-art approaches.
30
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Prototypical Networks for Few-shot Learning
Jake Snell, Kevin Swersky, Richard S. Zemel · arXiv (Cornell University) · 2017 · 5.2K citations · Full text
mixup: Beyond Empirical Risk Minimization
Hongyi Zhang, Moustapha Cissé, Yann Dauphin et al. · arXiv (Cornell University) · 2017 · 4.8K citations · Full text