Active learning with co-auxiliary learning and multi-level diversity for image classification

Z Wang, Z Chen, B Du - … on Circuits and Systems for Video …, 2023 - ieeexplore.ieee.org
Due to the fact that it is expensive and time-consuming to annotate a large amount of data,
the available labeled data to train a deep neural network is usually scarce, resulting in the …

Efficient 3D scene semantic segmentation via active learning on rendered 2D images

M Rong, H Cui, S Shen - IEEE Transactions on Image …, 2023 - ieeexplore.ieee.org
Inspired by Active Learning and 2D-3D semantic fusion, we proposed a novel framework for
3D scene semantic segmentation based on rendered 2D images, which could efficiently …

Fastal: Fast evaluation module for efficient dynamic deep active learning using broad learning system

S Sun, H Xu, Y Li, P Li, B Sheng… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
State-of-the-art Active Learning (AL) methods often encounter challenges associated with a
hysteretic learning process and an expensive data sampling mechanism. The former implies …

Active learning-based sample selection for label-efficient blind image quality assessment

T Song, L Li, D Cheng, P Chen… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Despite the considerable effort devoted to high-generalizable blind image quality
assessment (BIQA), the generalization performance of the state-of-the-art metrics remains …

3D semantic segmentation of aerial photogrammetry models based on orthographic projection

M Rong, S Shen - IEEE Transactions on Circuits and Systems …, 2023 - ieeexplore.ieee.org
Semantic segmentation of 3D scenes is one of the most important tasks in the field of
computer vision and has attracted much attention. In this paper, we propose a novel …

Active learning with effective scoring functions for semi-supervised temporal action localization

D Li, X Yang, Y Tang, C Zhang, W Zhang, L Ma - Displays, 2023 - Elsevier
Abstract Temporal Action Localization (TAL) aims to predict both action category and
temporal boundary of action instances in untrimmed videos, ie, start and end time. Existing …

[引用][C] Label-Efficient Point Cloud Semantic Segmentation: A Holistic Active Learning Approach

X Shi, L Cai, K Chen, CS Foo, K Jia… - World Scientific Annual …, 2024 - World Scientific
Deep learning models are the state-of-the-arts for semantic segmentation of point clouds,
the success of which relies on the availability of large-scale annotated datasets. However, it …