Improving replay sample selection and storage for less forgetting in continual learning
D Brignac, N Lobo… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Continual learning seeks to enable deep learners to train on a series of tasks of unknown
length without suffering from the catastrophic forgetting of previous tasks. One effective …
length without suffering from the catastrophic forgetting of previous tasks. One effective …
Rodd: A self-supervised approach for robust out-of-distribution detection
U Khalid, A Esmaeili, N Karim… - 2022 IEEE/CVF …, 2022 - ieeexplore.ieee.org
Recent studies have started to address the concern of detecting and rejecting the out-of-
distribution (OOD) samples as a major challenge in the safe deployment of deep learning …
distribution (OOD) samples as a major challenge in the safe deployment of deep learning …
[PDF][PDF] Unlocking the potential of federated learning: The symphony of dataset distillation via deep generative latents
Data heterogeneity presents significant challenges for federated learning (FL). Recently,
dataset distillation techniques have been introduced, and performed at the client level, to …
dataset distillation techniques have been introduced, and performed at the client level, to …
Self-representation based unsupervised exemplar selection in a union of subspaces
Finding a small set of representatives from an unlabeled dataset is a core problem in a
broad range of applications such as dataset summarization and information extraction …
broad range of applications such as dataset summarization and information extraction …
Group Distributionally Robust Dataset Distillation with Risk Minimization
Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic
dataset that captures the essential information of a training dataset, facilitating the training of …
dataset that captures the essential information of a training dataset, facilitating the training of …
Spectrum pursuit with residual descent for column subset selection problem: Theoretical guarantees and applications in deep learning
We propose a novel technique for dataset summarization by selecting representatives from
a large, unsupervised dataset. The approach is based on the concept of self-rank, defined …
a large, unsupervised dataset. The approach is based on the concept of self-rank, defined …
TMCOSS: Thresholded Multi-Criteria Online Subset Selection for Data-Efficient Autonomous Driving
S Das, H Patibandla, S Bhattacharya… - Proceedings of the …, 2021 - openaccess.thecvf.com
Training vision-based Autonomous driving models is a challenging problem with enormous
practical implications. One of the main challenges is the requirement of storage and …
practical implications. One of the main challenges is the requirement of storage and …
Two-way spectrum pursuit for cur decomposition and its application in joint column/row subset selection
The problem of simultaneous column and row subset selection is addressed in this paper.
The column space and row space of a matrix are spanned by its left and right singular …
The column space and row space of a matrix are spanned by its left and right singular …
Diva: Dataset derivative of a learning task
We present a method to compute the derivative of a learning task with respect to a dataset. A
learning task is a function from a training set to the validation error, which can be …
learning task is a function from a training set to the validation error, which can be …
Spectral pursuit for simultaneous sparse representation with accuracy guarantees
G Wan, H Schweitzer - International Journal of Data Science and Analytics, 2024 - Springer
The goal of simultaneous sparse representation is to capture as much information as
possible from a target matrix by a linear combination of several selected columns of another …
possible from a target matrix by a linear combination of several selected columns of another …