Results 81 to 90 of about 1,037,857 (302)

Cocoa semantic segmentation

, 2023
Semantic segmentation for cocoa disease using Mask R ...
Jamie Robert Sykes
core   +1 more source

RescueNet Semantic Segmentation Test Set

, 2023
Test set of RescueNet semantic ...
Tashnim Chowdhury (15470441), Maryam Rahnemoonfar (15470438), Robin Murphy (15470444)   +2 more
core   +1 more source

Distribution-Aware Margin Calibration for Semantic Segmentation in Images [PDF]

, 2021
The Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation. However, direct optimization of IoU score is very difficult because the learning objective is neither ...
Yu, L, Xu, M, Gao, Y, Luo, J, Li, Z, Zhang, J, Jian Zhang, Litao Yu, Min Xu, Jiebo Luo, Zhibin Li, Yongsheng Gao   +11 more
core   +1 more source

Toward Perception‐Native Electronic Skin: Bio‐Inspired In‐/Near‐Sensor and Neuromorphic Computing for Humanoid Robots

Advanced Materials Technologies, EarlyView.
Dense tactile streams from across the humanoid body converge on collide in a central wiring and data bottleneck. By relocating computation closer to and then into the skin itself, near‐ and in‐sensor architectures, together with neuromorphic computing, chart a path toward perception‐native electronic skin, in which the conversion of stimulus into ...
Mijin Kim, Chang‐Jae Beak, Jiyoung Park, Youngdo Jung, Sunjong Oh, Sin‐Hyung Lee, Bo‐Yeon Lee   +6 more
wiley   +1 more source

RescueNet Semantic Segmentation Train Set

, 2023
Train set of RescueNet semantic ...
Tashnim Chowdhury (15470441), Maryam Rahnemoonfar (15470438), Robin Murphy (15470444)   +2 more
core   +1 more source

Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback

Advanced Robotics Research, EarlyView.
BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat, Ali Umut Kaypak, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami   +4 more
wiley   +1 more source

WAILS: Watershed Algorithm With Image-Level Supervision for Weakly Supervised Semantic Segmentation

IEEE Access, 2019
Image semantic segmentation has great development in many fields, and the lack of fully supervised segmentation labels has always been a major problem in the development of image semantic segmentation.
Hongming Zhou, Kang Song, Xianglei Zhang, Wenyong Gui, Qiusuo Qian   +4 more
doaj   +1 more source

A SEMANTIC 3D POINT CLOUD SEGMENTATION APPROACH BASED ON OPTIMAL VIEW SELECTION FOR 2D IMAGE FEATURE EXTRACTION [PDF]

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2019
3D semantic segmentation is the joint task of partitioning a point cloud into semantically consistent 3D regions and assigning them to a semantic class/label. While the traditional approaches for 3D semantic segmentation typically rely only on structural
A. Adam, L. Grammatikopoulos, G. Karras, E. Protopapadakis, K. Karantzalos   +4 more
doaj   +1 more source

Federated unsupervised semantic segmentation

Neurocomputing
This work explores the application of Federated Learning (FL) to Unsupervised Semantic image Segmentation (USS). Recent USS methods extract pixel-level features using frozen visual foundation models and refine them through self-supervised objectives that encourage semantic grouping.
Charalambakis, Evangelos, Mygdalis, Vasileios, Pitas, Ioannis   +2 more
openaire   +4 more sources

Multilevel Embedding and Dropout for Improved 3D Object Detection in Autonomous Driving Systems

Advanced Robotics Research, EarlyView.
A plug‐in framework for RoI‐based 3D object detectors exploits previously untapped multi‐level information within RoI features. Its novel multi‐level embedding and dropout strategy enables the detection head to generate predictions at different feature levels.
Xiaohu Lu, Hayder Radha
wiley   +1 more source