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）
Muhammad Akhtar Munir, Muhammad Haris Khan, Salman Khan, Fahad Shahbaz Khan
Deep neural networks (DNNs) have enabled astounding progress in several vision-based problems. Despite showing high predictive accuracy, recently, several works have revealed that they tend to provide overconfident predictions and thus are poorly calibrated. The majority of the works addressing the miscalibration of DNNs fall under the scope of classification and consider only in-domain predictions. However, there is little to no progress in studying the calibration of DNN-based object detection models, which are central to many vision-based safety-critical applications. In this paper, inspired by the train-time calibration methods, we propose a novel auxiliary loss formulation that explicitly aims to align the class confidence of bounding boxes with the accurateness of predictions (i.e. precision). Since the original formulation of our loss depends on the counts of true positives and false positives in a minibatch, we develop a differentiable proxy of our loss that can be used during training with other application-specific loss functions. We perform extensive experiments on challenging in-domain and out-domain scenarios with six benchmark datasets including MS-COCO, Cityscapes, Sim10k, and BDD100k. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios. Our source code and pre-trained models are available at https://github.com/akhtarvision/bpc_calibration
Bridging Annotation Gaps: Transferring Labels to Align Object Detection Datasets
National University of Singapore I2R, A*STAR（新加坡国立大学I2R，A*STAR）；University of Cambridge（剑桥大学）；National University of Singapore ASUS Intelligent Cloud Services（新加坡国立大学ASUS智能云服务）
Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学耿丽人工智能学院）；Tsinghua University（清华大学）；Xidian University（西安电子科技大学）；Wuhan University（武汉大学）；Shanghai Jiao Tong University（上海交通大学）
SCMM: Calibrating Cross-modal Representations for Text-Based Person Search
College of Future Information Technology, Fudan University（复旦大学未来信息技术学院）；Department of Electrical and Computer Engineering, The University of British Columbia（不列颠哥伦比亚大学电气与计算机工程系）；College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；MEGVII Technology（MEGVII技术）；School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）；School of AI and CS, Nantong University（南通大学人工智能与计算机科学学院）；Academy of Artificial Intelligence, SMBU（SMBU人工智能学院）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）
PostHoc FREE Calibrating on Kolmogorov Arnold Networks
Institute for Clarity in Documentation（文献研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗康校区）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
Domain-adaptive and Subgroup-specific Cascaded Temperature Regression for Out-of-distribution Calibration
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）
Semantic-Aware Gaussian Process Calibration with Structured Layerwise Kernels for Deep Neural Networks
Next Generation Defence Multidisciplinary Technology Research Center, Pohang University of Science and Technology（下一代国防多学科技术研究中心，POSTECH大学）；Department of Electrical Engineering, Pohang University of Science and Technology（电气工程系，POSTECH大学）
