Learning Compositional Representations for Few-Shot Recognition
| Autor: | Pavel Tokmakov, Martial Hebert, Yu-Xiong Wang |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Deep learning Feature vector Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Linear subspace Regularization (mathematics) Bridging (programming) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer Natural language processing 0105 earth and related environmental sciences |
| Zdroj: | ICCV |
| Popis: | One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning ability is the compositional structure of concept representations in the human brain --- something that deep learning models are lacking. In this work, we make a step towards bridging this gap between human and machine learning by introducing a simple regularization technique that allows the learned representation to be decomposable into parts. Our method uses category-level attribute annotations to disentangle the feature space of a network into subspaces corresponding to the attributes. These attributes can be either purely visual, like object parts, or more abstract, like openness and symmetry. We demonstrate the value of compositional representations on three datasets: CUB-200-2011, SUN397, and ImageNet, and show that they require fewer examples to learn classifiers for novel categories. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|