English
Related papers

Related papers: WILD SAM: A Simulated-and-Real Data Augmentation f…

200 papers

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels,…

Computer Vision and Pattern Recognition · Computer Science 2022-01-03 Hengduo Li , Zuxuan Wu , Abhinav Shrivastava , Larry S. Davis

Autonomous vehicles (AVs) rely on environment perception and behavior prediction to reason about agents in their surroundings. These perception systems must be robust to adverse weather such as rain, fog, and snow. However, validation of…

Robotics · Computer Science 2022-03-29 Harrison Delecki , Masha Itkina , Bernard Lange , Ransalu Senanayake , Mykel J. Kochenderfer

We address multi-view pedestrian detection in a setting where labeled data is collected using a multi-camera setup different from the one used for testing. While recent multi-view pedestrian detectors perform well on the camera rig used for…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Erik Brorsson , Lennart Svensson , Kristofer Bengtsson , Knut Åkesson

In the realm of deploying Machine Learning-based Advanced Driver Assistance Systems (ML-ADAS) into real-world scenarios, adverse weather conditions pose a significant challenge. Conventional ML models trained on clear weather data falter…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Muhammad Zaeem Shahzad , Muhammad Abdullah Hanif , Muhammad Shafique

Reliable road segmentation in all weather conditions is critical for intelligent transportation applications, autonomous vehicles and advanced driver's assistance systems. For robust performance, all weather conditions should be included in…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Henrik Toikka , Eerik Alamikkotervo , Risto Ojala

The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require costly re-annotation for new environments, while standard…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Xi Xiao , Zhuxuanzi Wang , Mingqiao Mo , Chen Liu , Chenrui Ma , Yanshu Li , Smita Krishnaswamy , Xiao Wang , Tianyang Wang

LiDAR-based 3D object detection models have traditionally struggled under rainy conditions due to the degraded and noisy scanning signals. Previous research has attempted to address this by simulating the noise from rain to improve the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Xun Huang , Hai Wu , Xin Li , Xiaoliang Fan , Chenglu Wen , Cheng Wang

State-of-the-art techniques in weakly-supervised semantic segmentation (WSSS) using image-level labels exhibit severe performance degradation on driving scene datasets such as Cityscapes. To address this challenge, we develop a new WSSS…

Computer Vision and Pattern Recognition · Computer Science 2024-01-19 Dongseob Kim , Seungho Lee , Junsuk Choe , Hyunjung Shim

Detecting flying animals (e.g., birds, bats, and insects) using weather radar helps gain insights into animal movement and migration patterns, aids in management efforts (such as biosecurity) and enhances our understanding of the…

Machine Learning · Computer Science 2024-08-09 Mubin Ul Haque , Joel Janek Dabrowski , Rebecca M. Rogers , Hazel Parry

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Shuaijun Chen , Xu Jia , Jianzhong He , Yongjie Shi , Jianzhuang Liu

Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Heeji Yoon , Heeseong Shin , Eunbeen Hong , Hyunwook Choi , Hansang Cho , Daun Jeong , Seungryong Kim

Semi-supervised Camouflaged Object Detection (SSCOD) aims to reduce reliance on costly pixel-level annotations by leveraging limited annotated data and abundant unlabeled data. However, existing SSCOD methods based on Teacher-Student…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Xihang Hu , Fuming Sun , Jiazhe Liu , Feilong Xu , Xiaoli Zhang

Optical flow has made great progress in clean scenes, while suffers degradation under adverse weather due to the violation of the brightness constancy and gradient continuity assumptions of optical flow. Typically, existing methods mainly…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Hanyu Zhou , Yi Chang , Zhiwei Shi , Wending Yan , Gang Chen , Yonghong Tian , Luxin Yan

3D object detection is a central task for applications such as autonomous driving, in which the system needs to localize and classify surrounding traffic agents, even in the presence of adverse weather. In this paper, we address the problem…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Martin Hahner , Christos Sakaridis , Mario Bijelic , Felix Heide , Fisher Yu , Dengxin Dai , Luc Van Gool

Multimodal sensor fusion is an essential capability for autonomous robots, enabling object detection and decision-making in the presence of failing or uncertain inputs. While recent fusion methods excel in normal environmental conditions,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Edoardo Palladin , Roland Dietze , Praveen Narayanan , Mario Bijelic , Felix Heide

3D object detection networks tend to be biased towards the data they are trained on. Evaluation on datasets captured in different locations, conditions or sensors than that of the training (source) data results in a drop in model…

Computer Vision and Pattern Recognition · Computer Science 2021-12-02 Deepti Hegde , Vishal M. Patel

Recently, deep self-training approaches emerged as a powerful solution to the unsupervised domain adaptation. The self-training scheme involves iterative processing of target data; it generates target pseudo labels and retrains the network.…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Inkyu Shin , Sanghyun Woo , Fei Pan , InSo Kweon

Lidar sensors are often used in mobile robots and autonomous vehicles to complement camera, radar and ultrasonic sensors for environment perception. Typically, perception algorithms are trained to only detect moving and static objects as…

Computer Vision and Pattern Recognition · Computer Science 2019-09-04 Robin Heinzler , Philipp Schindler , Jürgen Seekircher , Werner Ritter , Wilhelm Stork

Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning optimises a model for the training domain, it…

Robotics · Computer Science 2017-09-19 Markus Wulfmeier , Alex Bewley , Ingmar Posner

Domain adaptation (DA) strives to mitigate the domain gap between the source domain where a model is trained, and the target domain where the model is deployed. When a deep learning model is deployed on an aerial platform, it may face…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Chowdhury Sadman Jahan , Andreas Savakis