2021
Rajasegaran, Jathushan; Khan, Salman; Hayat, Munawar; Khan, Fahad Shahbaz; Shah, Mubarak
Meta-learning the Learning Trends Shared Across Tasks Conference
British Machine Vision Conference, Nov 22-25, 2021.
Tags: BMVC, Few-Shot Learning, Meta-Learning | Links:
@conference{Rajasegaran2021,
title = {Meta-learning the Learning Trends Shared Across Tasks},
author = {Jathushan Rajasegaran and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Mubarak Shah},
url = {https://www.bmvc2021-virtualconference.com/conference/papers/paper_0874.html},
year = {2021},
date = {2021-11-22},
urldate = {2021-11-22},
booktitle = {British Machine Vision Conference, Nov 22-25},
keywords = {BMVC, Few-Shot Learning, Meta-Learning},
pubstate = {published},
tppubtype = {conference}
}
Rajasegaran, Jathushan; Khan, Salman; Hayat, Munawar; Khan, Fahad Shahbaz; Shah, Mubarak
Meta-learning the Learning Trends Shared Across Tasks Conference
British Machine Vision Conference, Nov 22-25, 2021.
Tags: BMVC, Few-Shot Learning, Meta-Learning | Links:
@conference{Rajasegaran2021b,
title = {Meta-learning the Learning Trends Shared Across Tasks},
author = {Jathushan Rajasegaran and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Mubarak Shah},
url = {https://www.bmvc2021-virtualconference.com/conference/papers/paper_0874.html},
year = {2021},
date = {2021-11-22},
urldate = {2021-11-22},
booktitle = {British Machine Vision Conference, Nov 22-25},
keywords = {BMVC, Few-Shot Learning, Meta-Learning},
pubstate = {published},
tppubtype = {conference}
}
2020
Rajasegaran, Jathushan; Khan, Salman; Hayat, Munawar; Khan, Fahad Shahbaz; Shah, Mubarak
iTAML : An Incremental Task-Agnostic Meta-learning Approach Conference
IEEE Conference on Computer Vision and Pattern Recognition, 2020.
Abstract | Tags: CVPR, Meta-Learning | Links:
@conference{Khan2020,
title = {iTAML : An Incremental Task-Agnostic Meta-learning Approach},
author = {Jathushan Rajasegaran and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/04/iTAML.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2020/04/iTAML-Supplementary.pdf},
year = {2020},
date = {2020-06-14},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
abstract = {Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous metalearning techniques, our approach is task-agnostic. When presented with a continuum of data, our model automatically identifies the task and quickly adapts to it with just a single update. We perform extensive experiments on five datasets in a class-incremental setting, leading to significant improvements over the state of the art methods (e.g., a 21.3% boost on CIFAR100 with 10 incremental tasks). Specifically, on large-scale datasets that generally prove difficult cases for incremental learning, our approach delivers absolute gains as high as 19.1% and 7.4% on ImageNet and MS-Celeb datasets, respectively. Our codes are available at: https://github.com/brjathu/iTAML.},
keywords = {CVPR, Meta-Learning},
pubstate = {published},
tppubtype = {conference}
}
Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous metalearning techniques, our approach is task-agnostic. When presented with a continuum of data, our model automatically identifies the task and quickly adapts to it with just a single update. We perform extensive experiments on five datasets in a class-incremental setting, leading to significant improvements over the state of the art methods (e.g., a 21.3% boost on CIFAR100 with 10 incremental tasks). Specifically, on large-scale datasets that generally prove difficult cases for incremental learning, our approach delivers absolute gains as high as 19.1% and 7.4% on ImageNet and MS-Celeb datasets, respectively. Our codes are available at: https://github.com/brjathu/iTAML.
Rajasegaran, Jathushan; Khan, Salman; Hayat, Munawar; Khan, Fahad Shahbaz; Shah, Mubarak
iTAML : An Incremental Task-Agnostic Meta-learning Approach Conference
IEEE Conference on Computer Vision and Pattern Recognition, 2020.
Abstract | Tags: CVPR, Meta-Learning | Links:
@conference{Khan2020d,
title = {iTAML : An Incremental Task-Agnostic Meta-learning Approach},
author = {Jathushan Rajasegaran and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/04/iTAML.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2020/04/iTAML-Supplementary.pdf},
year = {2020},
date = {2020-06-14},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
abstract = {Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous metalearning techniques, our approach is task-agnostic. When presented with a continuum of data, our model automatically identifies the task and quickly adapts to it with just a single update. We perform extensive experiments on five datasets in a class-incremental setting, leading to significant improvements over the state of the art methods (e.g., a 21.3% boost on CIFAR100 with 10 incremental tasks). Specifically, on large-scale datasets that generally prove difficult cases for incremental learning, our approach delivers absolute gains as high as 19.1% and 7.4% on ImageNet and MS-Celeb datasets, respectively. Our codes are available at: https://github.com/brjathu/iTAML.},
keywords = {CVPR, Meta-Learning},
pubstate = {published},
tppubtype = {conference}
}
Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous metalearning techniques, our approach is task-agnostic. When presented with a continuum of data, our model automatically identifies the task and quickly adapts to it with just a single update. We perform extensive experiments on five datasets in a class-incremental setting, leading to significant improvements over the state of the art methods (e.g., a 21.3% boost on CIFAR100 with 10 incremental tasks). Specifically, on large-scale datasets that generally prove difficult cases for incremental learning, our approach delivers absolute gains as high as 19.1% and 7.4% on ImageNet and MS-Celeb datasets, respectively. Our codes are available at: https://github.com/brjathu/iTAML.
2019
Khodadadeh, Siavash; Bölöni, Ladislau; Shah, Mubarak
Unsupervised Meta-Learning for Few-Shot Image Classification Conference
33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, 2019.
Tags: Meta-Learning, NeurIPS | Links:
@conference{Khodadadeh2019,
title = {Unsupervised Meta-Learning for Few-Shot Image Classification},
author = {Siavash Khodadadeh and Ladislau Bölöni and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/01/Publications_unsupervised-meta-learning-for-few-shot-image-classification.pdf
https://www.crcv.ucf.edu/research/projects/unsupervised-meta-learning-for-few-shot-image-and-video-classification/},
year = {2019},
date = {2019-11-30},
urldate = {2019-11-30},
booktitle = {33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada},
journal = {33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada},
keywords = {Meta-Learning, NeurIPS},
pubstate = {published},
tppubtype = {conference}
}
Khodadadeh, Siavash; Bölöni, Ladislau; Shah, Mubarak
Unsupervised Meta-Learning for Few-Shot Image Classification Conference
33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, 2019.
Tags: Meta-Learning, NeurIPS | Links:
@conference{Khodadadeh2019b,
title = {Unsupervised Meta-Learning for Few-Shot Image Classification},
author = {Siavash Khodadadeh and Ladislau Bölöni and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/01/Publications_unsupervised-meta-learning-for-few-shot-image-classification.pdf
https://www.crcv.ucf.edu/research/projects/unsupervised-meta-learning-for-few-shot-image-and-video-classification/},
year = {2019},
date = {2019-11-30},
urldate = {2019-11-30},
booktitle = {33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada},
journal = {33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada},
keywords = {Meta-Learning, NeurIPS},
pubstate = {published},
tppubtype = {conference}
}