Results 11 to 20 of about 4,472,392 (304)
Robust Loss Functions under Label Noise for Deep Neural Networks [PDF]
AAAI Conference on Artificial Intelligence, 2017 In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks
Ghosh, Aritra +2 more
core +2 more sources
Label-Free Concept Bottleneck Models [PDF]
International Conference on Learning Representations, 2023 Concept bottleneck models (CBM) are a popular way of creating more interpretable neural networks by having hidden layer neurons correspond to human-understandable concepts.
Tuomas P. Oikarinen +3 more
semanticscholar +1 more source
Asymmetric Loss For Multi-Label Classification [PDF]
IEEE International Conference on Computer Vision, 2020 In a typical multi-label setting, a picture contains on average few positive labels, and many negative ones. This positive-negative imbalance dominates the optimization process, and can lead to under-emphasizing gradients from positive labels during ...
Emanuel Ben Baruch +6 more
semanticscholar +1 more source
Masked Label Prediction: Unified Massage Passing Model for Semi-Supervised Classification [PDF]
International Joint Conference on Artificial Intelligence, 2020 Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification.
Yunsheng Shi +5 more
semanticscholar +1 more source
Part-based Pseudo Label Refinement for Unsupervised Person Re-identification [PDF]
Computer Vision and Pattern Recognition, 2022 Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques accomplish this task by using pseudo-labels, but these labels are inherently noisy and deteriorate ...
Yoonki Cho +3 more
semanticscholar +1 more source
Multi-Label Image Recognition With Graph Convolutional Networks [PDF]
Computer Vision and Pattern Recognition, 2019 The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model the label dependencies to improve the recognition performance.
Zhao-Min Chen +3 more
semanticscholar +1 more source
Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach [PDF]
Computer Vision and Pattern Recognition, 2016 We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and network ...
Giorgio Patrini +4 more
semanticscholar +1 more source
Unsupervised Person Re-Identification via Multi-Label Classification [PDF]
Computer Vision and Pattern Recognition, 2020 The challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels.
Dongkai Wang, Shiliang Zhang
semanticscholar +1 more source
MLCM: Multi-Label Confusion Matrix
IEEE Access, 2022 Concise and unambiguous assessment of a machine learning algorithm is key to classifier design and performance improvement. In the multi-class classification task, where each instance can only be labeled as one class, the confusion matrix is a powerful ...
M. Heydarian +2 more
semanticscholar +1 more source
Experimental Treatment with Favipiravir for COVID-19: An Open-Label Control Study
Engineering, 2020 An outbreak of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and its caused coronavirus disease 2019 (COVID-19) has been reported in China since December 2019.
Qingxian Cai +25 more
semanticscholar +1 more source