Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges
Recent advancements in perception for autonomous driving are driven by deep learning. In
order to achieve robust and accurate scene understanding, autonomous vehicles are …
order to achieve robust and accurate scene understanding, autonomous vehicles are …
Computer vision applications in offsite construction
The field of computer vision has undergone rapid growth in recent years, yet the use of
computer vision in offsite construction remains an under-researched area of study. Given the …
computer vision in offsite construction remains an under-researched area of study. Given the …
Collaborative multi-robot search and rescue: Planning, coordination, perception, and active vision
JP Queralta, J Taipalmaa, BC Pullinen, VK Sarker… - Ieee …, 2020 - ieeexplore.ieee.org
Search and rescue (SAR) operations can take significant advantage from supporting
autonomous or teleoperated robots and multi-robot systems. These can aid in mapping and …
autonomous or teleoperated robots and multi-robot systems. These can aid in mapping and …
Pp-liteseg: A superior real-time semantic segmentation model
Real-world applications have high demands for semantic segmentation methods. Although
semantic segmentation has made remarkable leap-forwards with deep learning, the …
semantic segmentation has made remarkable leap-forwards with deep learning, the …
Asymmetric non-local neural networks for semantic segmentation
The non-local module works as a particularly useful technique for semantic segmentation
while criticized for its prohibitive computation and GPU memory occupation. In this paper, we …
while criticized for its prohibitive computation and GPU memory occupation. In this paper, we …
In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images
Recent success of semantic segmentation approaches on demanding road driving datasets
has spurred interest in many related application fields. Many of these applications involve …
has spurred interest in many related application fields. Many of these applications involve …
Improving generalization in federated learning by seeking flat minima
Abstract Models trained in federated settings often suffer from degraded performances and
fail at generalizing, especially when facing heterogeneous scenarios. In this work, we …
fail at generalizing, especially when facing heterogeneous scenarios. In this work, we …
Semi-supervised semantic segmentation with prototype-based consistency regularization
Semi-supervised semantic segmentation requires the model to effectively propagate the
label information from limited annotated images to unlabeled ones. A challenge for such a …
label information from limited annotated images to unlabeled ones. A challenge for such a …
Cmda: Cross-modality domain adaptation for nighttime semantic segmentation
Most nighttime semantic segmentation studies are based on domain adaptation approaches
and image input. However, limited by the low dynamic range of conventional cameras …
and image input. However, limited by the low dynamic range of conventional cameras …
Hw-nas-bench: Hardware-aware neural architecture search benchmark
HardWare-aware Neural Architecture Search (HW-NAS) has recently gained tremendous
attention by automating the design of DNNs deployed in more resource-constrained daily …
attention by automating the design of DNNs deployed in more resource-constrained daily …