Two Heads are Better than One: Robust Learning Meets Multi-branch Models
Department of Computer Science, The University of Hong Kong（计算机科学系，香港大学）；Department of Electronic Engineering, Shanghai Jiao Tong University（电子工程系，上海交通大学）；Department of Electrical and Electronic Engineering, The University of Hong Kong（电气电子工程系，香港大学）；Department of Computer Science, City University of Hong Kong（计算机科学系，城市大学）；School of Computing, National University of Singapore（计算学院，新加坡国立大学）
Deep neural networks (DNNs) are vulnerable to adversarial examples, in which DNNs are misled to false outputs due to inputs containing imperceptible perturbations. Adversarial training, a reliable and effective method of defense, may significantly reduce the vulnerability of neural networks and becomes the de facto standard for robust learning. While many recent works practice the data-centric philosophy, such as how to generate better adversarial examples or use generative models to produce additional training data, we look back to the models themselves and revisit the adversarial robustness from the perspective of deep feature distribution as an insightful complementarity. In this paper, we propose \textit{Branch Orthogonality adveRsarial Training} (BORT) to obtain state-of-the-art performance with solely the original dataset for adversarial training. To practice our design idea of integrating multiple orthogonal solution spaces, we leverage a simple multi-branch neural network and propose a corresponding loss function, branch-orthogonal loss, to make each solution space of the multi-branch model orthogonal. We evaluate our approach on CIFAR-10, CIFAR-100 and SVHN against $\ell_{\infty}$ norm-bounded perturbations of size $ε= 8/255$, respectively. Exhaustive experiments are conducted to show that our method goes beyond all state-of-the-art methods without any tricks. Compared to all methods that do not use additional data for training, our models achieve 67.3\% and 41.5\% robust accuracy on CIFAR-10 and CIFAR-100 (improving upon the state-of-the-art by +7.23\% and +9.07\%).
D^3-Talker: Dual-Branch Decoupled Deformation Fields for Few-Shot 3D Talking Head Synthesis
School of Computer Science（计算机科学学院）；Software Engineering, Shenzhen University（软件工程，深圳大学）；Computer Vision Institute, School of Artificial Intelligence, Shenzhen University, Shenzhen, China（计算机视觉研究院，人工智能学院，深圳大学，深圳，中国）；Guangdong Provincial Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）；HBUG Lab, University of Exeter（HBUG实验室，埃克塞特大学）
Deep Head Pose Estimation from Depth Data for In-car Automotive Applications
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
最近，深度学习方法在计算机视觉的各个领域取得了令人鼓舞的成果。在本文中，我们通过卷积神经网络（CNN）来解决头部姿态估计问题。与文献中的其他提议不同，所描述的系统能够直接工作并且仅基于原始深度数据。此外，头部姿态估计被解决为回归问题，并且不依赖于视觉面部特征，如面部地标。我们在一个著名的公共数据集Biwi Kinect Head Pose上测试了我们的系统，表明我们的方法实现了最先进的结果，并且能够满足实时的性能要求。
Rectify the Regression Bias in Long-Tailed Object Detection
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）
SEGA: Drivable 3D Gaussian Head Avatar from a Single Image
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；ByteDance（字节跳动）；Pengcheng Lab（鹏城实验室）；Department of Automation, Tsinghua University（清华大学自动化系）
Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video
Department of Electronic Engineering, Tsinghua University, Beijing, China（清华大学电子工程系）；State Key Laboratory of Space Network and Communications（空间网络与通信国家重点实验室）；Beijing National Research Center for Information Science and Technology (BNRist)（北京国家信息科学与技术研究中心）；School of Computer Science and Technology, Xinjiang University, Urumqi, China（新疆大学计算机科学与技术学院）
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（教育部多媒体可信感知与高效计算重点实验室，厦门大学）；Shandong Inspur Database Technology Co.,Ltd（山东浪潮数据库技术有限公司）
Universitat Pompeu Fabra（庞培法布拉大学）；University of Adelaide（阿德莱德大学）；University of Surrey（萨里大学）；Catalan Institution for Research and Advanced Studies（加泰罗尼亚研究与高等研究院）
