A survey of label-efficient deep learning for 3D point clouds
In the past decade, deep neural networks have achieved significant progress in point cloud
learning. However, collecting large-scale precisely-annotated point clouds is extremely …
learning. However, collecting large-scale precisely-annotated point clouds is extremely …
A Low-Overhead Incorporation-Extrapolation based Few-Shot CSI Feedback Framework for Massive MIMO Systems
Accurate channel state information (CSI) is essential for downlink precoding in frequency
division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems with …
division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems with …
AIGCs confuse AI too: Investigating and explaining synthetic image-induced hallucinations in large vision-language models
Y Gao, J Wang, Z Lin, J Sang - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
The evolution of Artificial Intelligence Generated Contents (AIGCs) is advancing towards
higher quality. The growing interactions with AIGCs present a new challenge to the data …
higher quality. The growing interactions with AIGCs present a new challenge to the data …
Quality assurance for artificial intelligence: A study of industrial concerns, challenges and best practices
Quality Assurance (QA) aims to prevent mistakes and defects in manufactured products and
avoid problems when delivering products or services to customers. QA for AI systems …
avoid problems when delivering products or services to customers. QA for AI systems …
Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation
R Yoshihashi, Y Otsuka, T Tanaka… - Proceedings of the …, 2024 - openaccess.thecvf.com
The advance of generative models for images has inspired various training techniques for
image recognition utilizing synthetic images. In semantic segmentation, one promising …
image recognition utilizing synthetic images. In semantic segmentation, one promising …
Human-computer interactions with farm animals—enhancing welfare through precision livestock farming and artificial intelligence
While user-centered design approaches stemming from the human-computer interaction
(HCI) field have notably improved the welfare of companion, service, and zoo animals, their …
(HCI) field have notably improved the welfare of companion, service, and zoo animals, their …
DatasetNeRF: Efficient 3D-Aware Data Factory with Generative Radiance Fields
Progress in 3D computer vision tasks demands a huge amount of data, yet annotating multi-
view images with 3D-consistent annotations, or point clouds with part segmentation is both …
view images with 3D-consistent annotations, or point clouds with part segmentation is both …
Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding
Visual grounding aims to localize the image regions based on a textual query. Given the
difficulty of large-scale data curation, we investigate how to effectively learn visual grounding …
difficulty of large-scale data curation, we investigate how to effectively learn visual grounding …
Rulers2023: An Annotated Dataset of Synthetic and Real Images for Ruler Detection Using Deep Learning
D Matuzevičius - Electronics, 2023 - mdpi.com
This research investigates the usefulness and efficacy of synthetic ruler images for the
development of a deep learning-based ruler detection algorithm. Synthetic images offer a …
development of a deep learning-based ruler detection algorithm. Synthetic images offer a …
Can You Tell Real from Fake Face Images? Perception of Computer-Generated Faces by Humans
With recent advances in machine learning and big data, it is now possible to create synthetic
images that look real. Face generation is often of particular interest, as faces can be used for …
images that look real. Face generation is often of particular interest, as faces can be used for …