In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture Search (NAS) can work in synergy to greatly benefit on-device Dense Predictions (DP). Empirical results reveal that the joint learning of the two paradigms is surprisingly effective at improving DP accuracy, achieving superior performance over both the transfer learning of single-task NAS and prior state-of-the-art approaches in MTL, all with just 1/10th of the computation. To the best of our knowledge, our framework, named EDNAS, is the first to successfully leverage the synergistic relationship of NAS and MTL for DP. Our second key insight is that the standard depth training for multi-task DP can cause significant instability and noise to MTL evaluation. Instead, we propose JAReD, an improved, easy-to-adopt Joint Absolute-Relative Depth loss, that reduces up to 88% of the undesired noise while simultaneously boosting accuracy. We conduct extensive evaluations on standard datasets, benchmark against strong baselines and state-of-the-art approaches, as well as provide an analysis of the discovered optimal architectures.
InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search
School of Computer and Data Science, Fuzhou University(福州大学计算机与数据科学学院);School of Computer and Data Science, Minjiang University(闽江学院计算机与数据科学学院);School of Artificial Intelligence, Nanchang University(南昌大学人工智能学院);Department of Computer Science, Hong Kong Baptist University(香港浸会大学计算机科学系);School of Interdisciplinary Medicine and Engineering, Harbin Medical University(哈尔滨医科大学跨学科医学与工程学院)
SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation
Shanghai AI Laboratory(上海人工智能实验室);Zhejiang University(浙江大学);University of Maryland, College Park(马里兰大学 College Park 分校);Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学)
本文提出 SDAR 范式,将训练好的 AR 模型低成本转换为分块离散扩散模型,兼顾全局连贯与块内并行解码,并在密集及 MoE 模型上实现无损加速与推理提升。
CLASH: Complementary Learning with Neural Architecture Search for Gait Recognition
College of Computer Science, Zhejiang University(浙江大学计算机学院);School of Software Technology, Zhejiang University(浙江大学软件学院);Ant Group(蚂蚁集团);College of Computer Science and Technology, Zhejiang University(计算机科学与技术学院,浙江大学)
COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm
School of Computer Science and Technology, Tianjin University(天津大学计算机科学与技术学院);Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系);Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology(深圳先进技术大学计算机科学与人工智能学院)
SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心);Preferred Networks, Inc.(Preferred Networks公司)