Learning to see across Domains and Modalities

Abstract

Deep learning has raised hopes and expectations as a general solution for many applications; indeed it has proven effective, but it also showed a strong dependence on large quantities of data. Luckily, it has been shown that, even when data is scarce, a successful model can be trained by reusing prior knowledge. Thus, developing techniques for transfer learning, in its broadest definition, is a crucial element towards the deployment of effective and accurate intelligent systems. This thesis will focus on a family of transfer learning methods applied to the task of visual object recognition, specifically image classification. Transfer learning is a general term, and specific settings have been given specific names: when the learner has only access to unlabeled data from the a target domain and labeled data from a different domain (the source), the problem is known as that of "unsupervised domain adaptation" (DA). The first part of this work will focus on three methods for this setting: one of these methods deals with features, one with images while the third one uses both. The second part will focus on the real life issues of robotic perception, specifically RGB-D recognition. Robotic platforms are usually not limited to color perception; very often they also carry a Depth camera. Unfortunately, the depth modality is rarely used for visual recognition due to the lack of pretrained models from which to transfer and little data to train one on from scratch. Two methods for dealing with this scenario will be presented: one using synthetic data and the other exploiting cross-modality transfer learning.

References in corpus (21)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Distilling the Knowledge in a Neural Network
• Conditional Generative Adversarial Nets
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Frustratingly Easy Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Domain Separation Networks
• Domain Generalization via Invariant Feature Representation
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Revisiting Batch Normalization For Practical Domain Adaptation
• Good Practice in CNN Feature Transfer
• Deep Layer Aggregation
• Correlated and Individual Multi-Modal Deep Learning for RGB-D Object Recognition
• Domain Adaptation of Majority Votes via Perturbed Variation-based Label Transfer