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）
Adrian Galdran, Johan Verjans, Gustavo Carneiro, Miguel A. González Ballester
Delivering meaningful uncertainty estimates is essential for a successful deployment of machine learning models in the clinical practice. A central aspect of uncertainty quantification is the ability of a model to return predictions that are well-aligned with the actual probability of the model being correct, also known as model calibration. Although many methods have been proposed to improve calibration, no technique can match the simple, but expensive approach of training an ensemble of deep neural networks. In this paper we introduce a form of simplified ensembling that bypasses the costly training and inference of deep ensembles, yet it keeps its calibration capabilities. The idea is to replace the common linear classifier at the end of a network by a set of heads that are supervised with different loss functions to enforce diversity on their predictions. Specifically, each head is trained to minimize a weighted Cross-Entropy loss, but the weights are different among the different branches. We show that the resulting averaged predictions can achieve excellent calibration without sacrificing accuracy in two challenging datasets for histopathological and endoscopic image classification. Our experiments indicate that Multi-Head Multi-Loss classifiers are inherently well-calibrated, outperforming other recent calibration techniques and even challenging Deep Ensembles' performance. Code to reproduce our experiments can be found at \url{https://github.com/agaldran/mhml_calibration} .
Annealing Double-Head: An Architecture for Online Calibration of Deep Neural Networks
University of California, Santa Cruz（加州大学圣克鲁兹分校）；Institute of Theoretical Physics, Chinese Academy of Sciences（中国科学院理论物理研究所）；National University of Singapore（新加坡国立大学）
Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Beijing Key Laboratory of Big Data Management and Analysis Methods（大数据管理与分析方法北京市重点实验室）
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Yam Pak Charitable Foundation School of Computing and Information Sciences, Saint Francis University（圣弗朗西斯大学计算与信息科学学院（严炳慈善基金会冠名））；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation
Ping An Technology（平安科技）
我们解决了具有挑战性的问题，基于RGB图像的头部姿态估计。我们首先重新制定头部姿势表示学习，以限制它到一个有界的空间。头部姿态表示为矢量投影或矢量角度有助于提高性能。此外，提出了一种结合MSE回归损失的排序损失。排名损失监督具有相同人的配对样本的神经网络，并惩罚姿势预测的不正确排序。对这个新的损失函数的分析表明，它有助于更好的局部特征提取器，其中特征被概括为抽象地标，抽象地标是姿势相关的特征，而不是姿势无关的信息，如身份，年龄和照明。大量的实验表明，我们的方法显着优于当前国家的最先进的计划在公共数据集：AFLW2000和BIWI。我们的模型实现了显着的改善，比以前的SOTA MAE AFLW2000和BIWI分别从4.50到3.66和从4.0到3.71。源代码将在https://github.com/seathiefwang/RankHeadPose上提供。
Using Cross-Domain Detection Loss to Infer Multi-Scale Information for Improved Tiny Head Tracking
Department of Electrical and Computer Engineering, University of Nebraska-Lincoln（内布拉斯加大学林肯分校电气与计算机工程系）；Department of Electrical and Computer Engineering, University of Maryland（马里兰大学电气与计算机工程系）；Department of Electrical and Computer Engineering, University of Arizona（亚利桑那大学电气与计算机工程系）
Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection
Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Information Technology University（信息技术大学）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）
Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions
Engineering Sciences, Homi Bhabha National Institute Training School Complex（工程科学，霍米·巴赫瓦全国研究所培训学校）；Computer and Informatics Group, VECC 1/AF（计算机与信息组，VECC 1/AF）
Towards Improving Calibration in Object Detection Under Domain Shift
Information Technology University of Punjab（旁遮普信息技术大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Mercedes-Benz Tech Innovation（梅赛德斯-奔驰技术创新公司）
SurgNavAR: An Augmented Reality Surgical Navigation Framework for Optical See-Through Head Mounted Displays
Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC（鹿特丹伊拉斯姆斯大学医学中心放射与核医学系鹿特丹生物医学成像组）；Department of Oral and Maxillofacial Surgery, Erasmus MC（鹿特丹伊拉斯姆斯大学医学中心口腔颌面外科）；University of Groningen（格罗宁根大学）；Department of High Performance Compute & Visualization, SURF bv（SURF bv高性能计算与可视化部）；Department of Neurosurgery, Erasmus MC（鹿特丹伊拉斯姆斯大学医学中心神经外科）；Trauma Research Unit, Department of Surgery, Erasmus MC（鹿特丹伊拉斯姆斯大学医学中心外科创伤研究单元）
Optimizing Calibration by Gaining Aware of Prediction Correctness
The Australian National University（澳大利亚国立大学）；Data61, The Commonwealth Scientific and Industrial Research Organisation（联邦科学与工业研究组织Data61）；The Hong Kong Polytechnic University（香港理工大学）；Stanford University（斯坦福大学）
