English
Related papers

Related papers: Improving Uncertainty of Deep Learning-based Objec…

200 papers

As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing methods address this problem in various directions, they…

Machine Learning · Computer Science 2022-11-30 Jongwoo Ko , Bongsoo Yi , Se-Young Yun

Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to…

Artificial Intelligence · Computer Science 2017-05-08 Xiaowei Huang , Marta Kwiatkowska , Sen Wang , Min Wu

Central to human-aligned AI is understanding the benefits of human-elicited labels over synthetic alternatives. While human soft-labels improve calibration by capturing uncertainty, prior studies conflate these benefits with the implicit…

Machine Learning · Computer Science 2026-05-19 Maja Pavlovic , Silviu Paun , Massimo Poesio

Object detection in autonomous driving applications implies that the detection and tracking of semantic objects are commonly native to urban driving environments, as pedestrians and vehicles. One of the major challenges in state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 G. Melotti , W. Lu , P. Conde , D. Zhao , A. Asvadi , N. Gonçalves , C. Premebida

This paper proposes a self-explainable Deep Learning (SE-DL) system for an image classification problem that performs self-error detection. The self-error detection is key to improving the DL system's safe operation, especially in…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Mohammad Mahdi Karimi , Azin Heidarshenas , William W. Edmonson

Most existing weakly supervised localization (WSL) approaches learn detectors by finding positive bounding boxes based on features learned with image-level supervision. However, those features do not contain spatial location related…

Computer Vision and Pattern Recognition · Computer Science 2017-05-02 Zequn Jie , Yunchao Wei , Xiaojie Jin , Jiashi Feng , Wei Liu

Modern visual recognition models often display overconfidence due to their reliance on complex deep neural networks and one-hot target supervision, resulting in unreliable confidence scores that necessitate calibration. While current…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Tianshui Chen , Weihang Wang , Tao Pu , Jinghui Qin , Zhijing Yang , Jie Liu , Liang Lin

Unlike nature image classification where groundtruth label is explicit and of no doubt, physicians commonly interpret medical image conditioned on certainty like using phrase "probable" or "likely". Existing medical image datasets either…

Machine Learning · Computer Science 2025-11-21 Kunyu Zhang , Fukang Ge , Binyang Wang , Yingke Chen , Kazuma Kobayashi , Lin Gu , Jinhao Bi , Yingying Zhu

Learning-based algorithms for automated license plate recognition implicitly assume that the training and test data are well aligned. However, this may not be the case under extreme environmental conditions, or in forensic applications…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Franziska Schirrmacher , Benedikt Lorch , Anatol Maier , Christian Riess

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…

Computer Vision and Pattern Recognition · Computer Science 2023-11-10 Muhammad Akhtar Munir , Muhammad Haris Khan , M. Saquib Sarfraz , Mohsen Ali

Modern machine learning pipelines, in particular those based on deep learning (DL) models, require large amounts of labeled data. For classification problems, the most common learning paradigm consists of presenting labeled examples during…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Jacopo Teneggi , Paul H. Yi , Jeremias Sulam

Semantic segmentation of 3D LiDAR point clouds is important in urban remote sensing for understanding real-world street environments. This task, by projecting LiDAR point clouds and 3D semantic labels as sparse maps, can be reformulated as…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Xiaoyu Dong , Tiankui Xian , Wanshui Gan , Naoto Yokoya

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in…

Computer Vision and Pattern Recognition · Computer Science 2017-08-15 Zhuo Chen , Weisi Lin , Shiqi Wang , Long Xu , Leida Li

Radars are widely used to obtain echo information for effective prediction, such as precipitation nowcasting. In this paper, recent relevant scientific investigation and practical efforts using Deep Learning (DL) models for weather radar…

Computer Vision and Pattern Recognition · Computer Science 2023-11-17 Qi Liu , Zhiyun Yang , Ru Ji , Yonghong Zhang , Muhammad Bilal , Xiaodong Liu , S Vimal , Xiaolong Xu

Deep learning has played a major role in the interpretation of dermoscopic images for detecting skin defects and abnormalities. However, current deep learning solutions for dermatological lesion analysis are typically limited in providing…

Computer Vision and Pattern Recognition · Computer Science 2021-07-20 Gun-Hee Lee , Han-Bin Ko , Seong-Whan Lee

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…

Computer Vision and Pattern Recognition · Computer Science 2019-02-22 Yongcheng Liu , Lu Sheng , Jing Shao , Junjie Yan , Shiming Xiang , Chunhong Pan

Understanding the scene is key for autonomously navigating vehicles and the ability to segment the surroundings online into moving and non-moving objects is a central ingredient for this task. Often, deep learning-based methods are used to…

Capturing uncertainty in object detection is indispensable for safe autonomous driving. In recent years, deep learning has become the de-facto approach for object detection, and many probabilistic object detectors have been proposed.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-13 Di Feng , Ali Harakeh , Steven Waslander , Klaus Dietmayer

Robust road segmentation in all road conditions is required for safe autonomous driving and advanced driver assistance systems. Supervised deep learning methods provide accurate road segmentation in the domain of their training data but…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Eerik Alamikkotervo , Henrik Toikka , Kari Tammi , Risto Ojala

The objective of machine unlearning (MU) is to eliminate previously learned data from a model. However, it is challenging to strike a balance between computation cost and performance when using existing MU techniques. Taking inspiration…

Machine Learning · Computer Science 2024-06-13 Zonglin Di , Zhaowei Zhu , Jinghan Jia , Jiancheng Liu , Zafar Takhirov , Bo Jiang , Yuanshun Yao , Sijia Liu , Yang Liu