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.
Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation
College of Computer and Cyber Security, Fujian Normal University（计算机与网络安全部，福建师范大学）；Department of Computer Science, National Tsing Hua University（计算机科学系，国立清华大学）
Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation
Northwestern University（西北大学）；Futurewei Technologies（华为未来技术研究院）；University of Electronic Science and Technology of China（电子科技大学）；University of Rochester（罗切斯特大学）
DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing
Great Bay University（大西洋大学）；University of Science and Technology of China（中国科学技术大学）；Dongguan Key Laboratory for Intelligence and Information Technology（东莞智能与信息技术重点实验室）；GRGBanking Equipment Co., Ltd.（GRGBanking设备有限公司）；South China University of Technology（华南理工大学）；Lappeenranta University of Technology（拉普兰塔理工大学）；Macao Polytechnic University（澳门理工学院）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）
Hypergraph Tversky-Aware Domain Incremental Learning for Brain Tumor Segmentation with Missing Modalities
College of Computer and Control Engineering, Northeast Forestry University（东北林业大学计算机与控制工程学院）；The Centre for Healthy Brain Ageing (CHeBA), UNSW（健康脑年龄中心（CHeBA），UNSW）；School of Computer Science and Engineering, UNSW（计算机科学与工程学院，UNSW）；School of Software, Tsinghua University（清华大学软件学院）；Centre for Health Informatics, Macquarie University（健康信息学中心，麦考瑞大学）
Instance Segmentation of Unlabeled Modalities via Cyclic Segmentation GAN
Harvard University（哈佛大学）；Technical University of Munich（慕尼黑工业大学）；MIT（麻省理工学院）；University of Cambridge（剑桥大学）；Donostia International Physics Center（多诺斯蒂亚国际物理中心）；University of the Basque Country（巴斯克大学）；Ikerbasque, Basque Foundation for Science（巴斯克科学基金会伊克巴斯克）；HHMI（霍华德·休斯医学研究所）；Boston College（波士顿学院）
UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities
Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Khalifa University（哈利法大学）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）；EPFL（洛桑联邦理工学院）
Towards Stable Cross-Domain Depression Recognition under Missing Modalities
School of Future Technology, South China University of Technology（未来技术学院，华南理工大学）；PengCheng Laboratory（鹏城实验室）；School of Software Engineering, South China University of Technology（软件工程学院，华南理工大学）；Artificial Intelligence Research Institute, Shenzhen MSU-BIT University（人工智能研究院，深圳MSU-BIT大学）；Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing（粤港澳大湾区情感智能与泛在计算联合实验室）；School of Computer Science and Technology, Guangdong University of Technology（计算机科学与技术学院，广东工业大学）；Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）
Unsupervised Cross-Modality Domain Adaptation for Vestibular Schwannoma Segmentation and Koos Grade Prediction based on Semi-Supervised Contrastive Learning
Radboud University Medical Center（拉德堡德大学医学中心）；The Netherlands Cancer Institute（荷兰癌症研究所）；Nanjing University of Information Science and Technology（南京信息工程大学）
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos
Columbia University（哥伦比亚大学）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；University of Central Florida（中佛罗里达大学）；Goethe University Frankfurt（法兰克福大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research AI（IBM研究院人工智能部门）；UT Austin（德克萨斯大学奥斯汀分校）；NYU（纽约大学）
CAR-MFL: Cross-Modal Augmentation by Retrieval for Multimodal Federated Learning with Missing Modalities
NepAl Applied Mathematics and Informatics Institute for research（尼泊尔应用数学与信息学研究所）；Fogsphere (Redev.AI)（Fogsphere（Redev.AI））；University of Lausanne（洛桑大学）；West Virginia University（西弗吉尼亚大学）；University of Aberdeen（阿伯丁大学）
DNA-Prior: Unsupervised Denoise Anything via Dual-Domain Prior
University of Cambridge（剑桥大学）；Lucerne University Teaching and Research Hospital（卢塞恩教学与研究医院）；Zurich University of Applied Sciences（苏黎世应用科学大学）；YMSC, Tsinghua University（清华大学数学科学中心）
