Label Efficient Learning of Transferable Representations across Domains and Tasks
arXiv:1712.00123
Abstract
We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task using a metric learning-based approach. Our model is simultaneously optimized on labeled source data and unlabeled or sparsely labeled data in the target domain. Our method shows compelling results on novel classes within a new domain even when only a few labeled examples per class are available, outperforming the prevalent fine-tuning approach. In addition, we demonstrate the effectiveness of our framework on the transfer learning task from image object recognition to video action recognition.
arXiv commentNIPS 2017
References in corpus (21)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Deep Domain Confusion: Maximizing for Domain Invariance
- Matching Networks for One Shot Learning
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- Adversarial Feature Learning
- Adversarially Learned Inference
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- Beyond Sharing Weights for Deep Domain Adaptation
- Adversarial Discriminative Domain Adaptation
- Unsupervised Cross-Domain Image Generation
- Revisiting Batch Normalization For Practical Domain Adaptation
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation
- Domain Adaptation for Visual Applications: A Comprehensive Survey
- Deep Transfer Network: Unsupervised Domain Adaptation
- Deep Transfer Learning with Joint Adaptation Networks
- Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
- Unsupervised Learning of Long-Term Motion Dynamics for Videos