Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
arXiv:1803.00068
Abstract
Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels. We propose that advantages may be derived by combining them, in the form of different insights that lead to a novel design and complementary properties that result in better performance. At the feature level, inspired by insights from semi-supervised learning, we propose a classification-aware domain adversarial neural network that brings target examples into more classifiable regions of source domain. Next, we posit that computer vision insights are more amenable to injection at the pixel level. In particular, we use 3D geometry and image synthesis based on a generalized appearance flow to preserve identity across pose transformations, while using an attribute-conditioned CycleGAN to translate a single source into multiple target images that differ in lower-level properties such as lighting. Besides standard UDA benchmark, we validate on a novel and apt problem of car recognition in unlabeled surveillance images using labeled images from the web, handling explicitly specified, nameable factors of variation through pixel-level and implicit, unspecified factors through feature-level adaptation.
arXiv commentAccepted to CVPR 2019
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Conditional Generative Adversarial Nets
- Deep Domain Confusion: Maximizing for Domain Invariance
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Unsupervised Domain Adaptation with Residual Transfer Networks
- Deep Convolutional Inverse Graphics Network
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Domain Separation Networks
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
- Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
- Least Squares Generative Adversarial Networks