Deep learning in human activity recognition with wearable sensors: A review on advances
Mobile and wearable devices have enabled numerous applications, including activity
tracking, wellness monitoring, and human–computer interaction, that measure and improve …
tracking, wellness monitoring, and human–computer interaction, that measure and improve …
Quality not quantity: On the interaction between dataset design and robustness of clip
Web-crawled datasets have enabled remarkable generalization capabilities in recent image-
text models such as CLIP (Contrastive Language-Image pre-training) or Flamingo, but little …
text models such as CLIP (Contrastive Language-Image pre-training) or Flamingo, but little …
OpenFL: the open federated learning library
P Foley, MJ Sheller, B Edwards, S Pati… - Physics in Medicine …, 2022 - iopscience.iop.org
Objective. Federated learning (FL) is a computational paradigm that enables organizations
to collaborate on machine learning (ML) and deep learning (DL) projects without sharing …
to collaborate on machine learning (ML) and deep learning (DL) projects without sharing …
A review of the role of causality in developing trustworthy ai systems
State-of-the-art AI models largely lack an understanding of the cause-effect relationship that
governs human understanding of the real world. Consequently, these models do not …
governs human understanding of the real world. Consequently, these models do not …
Adversarial filters of dataset biases
R Le Bras, S Swayamdipta… - International …, 2020 - proceedings.mlr.press
Large neural models have demonstrated human-level performance on language and vision
benchmarks, while their performance degrades considerably on adversarial or out-of …
benchmarks, while their performance degrades considerably on adversarial or out-of …
Domain adaptation with conditional distribution matching and generalized label shift
R Tachet des Combes, H Zhao… - Advances in Neural …, 2020 - proceedings.neurips.cc
Adversarial learning has demonstrated good performance in the unsupervised domain
adaptation setting, by learning domain-invariant representations. However, recent work has …
adaptation setting, by learning domain-invariant representations. However, recent work has …
Umix: Improving importance weighting for subpopulation shift via uncertainty-aware mixup
Subpopulation shift widely exists in many real-world machine learning applications, referring
to the training and test distributions containing the same subpopulation groups but varying in …
to the training and test distributions containing the same subpopulation groups but varying in …
Comparing handcrafted features and deep neural representations for domain generalization in human activity recognition
N Bento, J Rebelo, M Barandas, AV Carreiro… - Sensors, 2022 - mdpi.com
Human Activity Recognition (HAR) has been studied extensively, yet current approaches are
not capable of generalizing across different domains (ie, subjects, devices, or datasets) with …
not capable of generalizing across different domains (ie, subjects, devices, or datasets) with …
Fedbr: Improving federated learning on heterogeneous data via local learning bias reduction
Federated Learning (FL) is a way for machines to learn from data that is kept locally, in order
to protect the privacy of clients. This is typically done using local SGD, which helps to …
to protect the privacy of clients. This is typically done using local SGD, which helps to …
Disentanglement of correlated factors via hausdorff factorized support
A grand goal in deep learning research is to learn representations capable of generalizing
across distribution shifts. Disentanglement is one promising direction aimed at aligning a …
across distribution shifts. Disentanglement is one promising direction aimed at aligning a …