Multi-domain active learning: Literature review and comparative study
Multi-domain learning (MDL) refers to learning a set of models simultaneously, where each
model is specialized to perform a task in a particular domain. Generally, a high labeling …
model is specialized to perform a task in a particular domain. Generally, a high labeling …
You never get a second chance to make a good first impression: Seeding active learning for 3d semantic segmentation
We propose SeedAL, a method to seed active learning for efficient annotation of 3D point
clouds for semantic segmentation. Active Learning (AL) iteratively selects relevant data …
clouds for semantic segmentation. Active Learning (AL) iteratively selects relevant data …
Active Learning-DETR: Cost-Effective Object Detection for Kitchen Waste
H Qin, L Shu, L Zhou, S Deng, H **ao… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Object detection in kitchen waste faces numerous challenges, including a variety of target
categories, significant morphological variations, and complex backgrounds, coupled with the …
categories, significant morphological variations, and complex backgrounds, coupled with the …
Image Classification with Deep Reinforcement Active Learning
M Jiu, X Song, H Sahbi, S Li, Y Chen, W Guo… - arxiv preprint arxiv …, 2024 - arxiv.org
Deep learning is currently reaching outstanding performances on different tasks, including
image classification, especially when using large neural networks. The success of these …
image classification, especially when using large neural networks. The success of these …
[PDF][PDF] 基于主动学**的图像分类技术: 现状与未来
刘颖， 庞羽良， 张伟东， **大湘， 许志杰 - 电子学报, 2023 - ejournal.org.cn
图像分类作为计算机视觉领域中的重要研究方向之一, 应用领域非常广泛. 基于深度学**的图像
分类技术取得的成功, 依赖大量的已标注数据, 然而数据的标注成本往往是昂贵的 …
分类技术取得的成功, 依赖大量的已标注数据, 然而数据的标注成本往往是昂贵的 …
GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise
M Mots' oehli - arxiv preprint arxiv:2411.05939, 2024 - arxiv.org
Active learning aims to train accurate classifiers while minimizing labeling costs by
strategically selecting informative samples for annotation. This study focuses on image …
strategically selecting informative samples for annotation. This study focuses on image …
Best practices in pool-based active learning for image classification
The recent popularity of active learning (AL) methods for image classification using deep-
learning has led to a large number of publications that lead to significant progress in the …
learning has led to a large number of publications that lead to significant progress in the …
EnCoDe: Enhancing Compressed Deep Learning Models Through Feature---Distillation and Informative Sample Selection
This paper presents Encode, a novel technique that merges active learning, model
compression, and knowledge distillation to optimize deep learning models. The method …
compression, and knowledge distillation to optimize deep learning models. The method …
Not All Samples Are Created Equal: Task-Aware Informative Sampling and Adaptive Inference for Efficient Edge AI
R Gaire - 2024 - digitalcommons.unl.edu
The rapid proliferation of Internet of Things (IoT) devices has resulted in an unprecedented
influx of data generated at the edge by billions of sensors. Traditional approaches relying on …
influx of data generated at the edge by billions of sensors. Traditional approaches relying on …