Deep convolutional networks are ubiquitous in computer vision, due to their excellent performance across different tasks for various domains. Models are, however, often trained in isolation for each task, failing to exploit relatedness between tasks and domains to learn more compact models that generalise better in low-data regimes. Multi-domain learning aims to handle related tasks, such as image classification across multiple domains, simultaneously. Previous work on this problem explored the use of a pre-trained and fixed domain-agnostic base network, in combination with smaller learnable domain-specific adaptation modules. In this paper, we introduce Modulation Adapters, which update the convolutional filter weights of the model in a multiplicative manner for each task. Parameterising these adaptation weights in a factored manner allows us to scale the number of per-task parameters in a flexible manner, and to strike different parameter-accuracy trade-offs. We evaluate our approach on the Visual Decathlon challenge, composed of ten image classification tasks across different domains, and on the ImageNet-to-Sketch benchmark, which consists of six image classification tasks. Our approach yields excellent results, with accuracies that are comparable to or better than those of existing state-of-the-art approaches.
Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Kolors Team, Kuaishou Technology（快手科技Kolors团队）；Shenzhen Loop Area Institute, Shenzhen, China（深圳循环区研究所）；Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China（广东大数据分析与处理重点实验室）；South China University of Technology, Guangzhou, China（华南理工大学）
What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning
College of Computer Science, Zhejiang University（浙江大学计算机学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Shanghai Institute for Advanced Study, Zhejiang University（浙江大学上海高等研究院）
Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation
Shanghai Jiao Tong University（上海交通大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；The Chinese University of Hong Kong（香港中文大学）
PET-Adapter: Test-Time Domain Adaptation for Full and Limited-Angle PET Image Reconstruction
Institute of Imaging and Computer Vision, RWTH Aachen University, Germany（成像与计算机视觉研究所，亚琛工业大学，德国）；Machine Learning for Medical Data, Heinrich Heine University Düsseldorf, Germany（医学数据机器学习，杜伊斯堡-艾森大学，德国）
DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
Intelligent Software Research Center, Institute of Software, CAS（中国科学院软件研究所智能软件研究中心）；State Key Lab of Processors, Institute of Computing Technology, CAS（中国科学院计算技术研究所处理器国家重点实验室）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）
UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval
Zhejiang University（浙江大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）；Dalian University of Technology（大连理工大学）；DAMO Academy, Alibaba Group（阿里巴巴达摩院）；Microsoft Research（微软研究院）
ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
National Key Laboratory for Multimedia Information Processing（多媒体信息处理国家重点实验室）；The Chinese University of Hong Kong（香港中文大学）；Hong Kong University of Science and Technology（香港科技大学）；School of Computer Science Peking University（北京大学计算机学院）；AIRobotics
Semantic Relation-Enhanced CLIP Adapter for Domain Adaptive Zero-Shot Learning
School of Computer Science and Technology, East China Normal University, China（东华大学计算机科学与技术学院）；College of Computer Science and Technology, Ocean University of China, China（中国海洋大学计算机科学与技术学院）
BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
College of Artificial Intelligence, Xi’an Jiaotong University（西安交通大学人工智能学院）；Shenzhen University of Advanced Technology（深圳先进技术大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件工程学院）
