A survey of deep active learning

P Ren, Y **ao, X Chang, PY Huang, Z Li… - ACM computing …, 2021‏ - dl.acm.org
Active learning (AL) attempts to maximize a model's performance gain while annotating the
fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount …

A review of object detection based on deep learning

Y **ao, Z Tian, J Yu, Y Zhang, S Liu, S Du… - Multimedia Tools and …, 2020‏ - Springer
With the rapid development of deep learning techniques, deep convolutional neural
networks (DCNNs) have become more important for object detection. Compared with …

Pervasive label errors in test sets destabilize machine learning benchmarks

CG Northcutt, A Athalye, J Mueller - arxiv preprint arxiv:2103.14749, 2021‏ - arxiv.org
We identify label errors in the test sets of 10 of the most commonly-used computer vision,
natural language, and audio datasets, and subsequently study the potential for these label …

Federated learning for generalization, robustness, fairness: A survey and benchmark

W Huang, M Ye, Z Shi, G Wan, H Li… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Federated learning has emerged as a promising paradigm for privacy-preserving
collaboration among different parties. Recently, with the popularity of federated learning, an …

[PDF][PDF] The computational limits of deep learning

NC Thompson, K Greenewald, K Lee… - arxiv preprint arxiv …, 2020‏ - assets.pubpub.org
Deep learning's recent history has been one of achievement: from triumphing over humans
in the game of Go to world-leading performance in image classification, voice recognition …

Do adversarially robust imagenet models transfer better?

H Salman, A Ilyas, L Engstrom… - Advances in Neural …, 2020‏ - proceedings.neurips.cc
Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …

Narcissus: A practical clean-label backdoor attack with limited information

Y Zeng, M Pan, HA Just, L Lyu, M Qiu… - Proceedings of the 2023 …, 2023‏ - dl.acm.org
Backdoor attacks introduce manipulated data into a machine learning model's training set,
causing the model to misclassify inputs with a trigger during testing to achieve a desired …

A review of single-source deep unsupervised visual domain adaptation

S Zhao, X Yue, S Zhang, B Li, H Zhao… - … on Neural Networks …, 2020‏ - ieeexplore.ieee.org
Large-scale labeled training datasets have enabled deep neural networks to excel across a
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …

Deep learning for generic object detection: A survey

L Liu, W Ouyang, X Wang, P Fieguth, J Chen… - International journal of …, 2020‏ - Springer
Object detection, one of the most fundamental and challenging problems in computer vision,
seeks to locate object instances from a large number of predefined categories in natural …

Universal domain adaptation through self supervision

K Saito, D Kim, S Sclaroff… - Advances in neural …, 2020‏ - proceedings.neurips.cc
Unsupervised domain adaptation methods traditionally assume that all source categories
are present in the target domain. In practice, little may be known about the category overlap …