A survey of deep active learning
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 …
fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount …
A review of object detection based on deep learning
With the rapid development of deep learning techniques, deep convolutional neural
networks (DCNNs) have become more important for object detection. Compared with …
networks (DCNNs) have become more important for object detection. Compared with …
Pervasive label errors in test sets destabilize machine learning benchmarks
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 …
natural language, and audio datasets, and subsequently study the potential for these label …
Federated learning for generalization, robustness, fairness: A survey and benchmark
Federated learning has emerged as a promising paradigm for privacy-preserving
collaboration among different parties. Recently, with the popularity of federated learning, an …
collaboration among different parties. Recently, with the popularity of federated learning, an …
[PDF][PDF] The computational limits of deep learning
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 …
in the game of Go to world-leading performance in image classification, voice recognition …
Do adversarially robust imagenet models transfer better?
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 …
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …
Narcissus: A practical clean-label backdoor attack with limited information
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 …
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
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 …
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …
Deep learning for generic object detection: A survey
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 …
seeks to locate object instances from a large number of predefined categories in natural …
Universal domain adaptation through self supervision
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 …
are present in the target domain. In practice, little may be known about the category overlap …