Weight-sharing neural architecture search: A battle to shrink the optimization gap
Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …
individual search methods have been replaced by weight-sharing search methods for higher …
Rmm: Reinforced memory management for class-incremental learning
Abstract Class-Incremental Learning (CIL)[38] trains classifiers under a strict memory
budget: in each incremental phase, learning is done for new data, most of which is …
budget: in each incremental phase, learning is done for new data, most of which is …
Architecture matters in continual learning
A large body of research in continual learning is devoted to overcoming the catastrophic
forgetting of neural networks by designing new algorithms that are robust to the distribution …
forgetting of neural networks by designing new algorithms that are robust to the distribution …
Memory-efficient class-incremental learning for image classification
With the memory-resource-limited constraints, class-incremental learning (CIL) usually
suffers from the “catastrophic forgetting” problem when updating the joint classification …
suffers from the “catastrophic forgetting” problem when updating the joint classification …
Class-incremental exemplar compression for class-incremental learning
Exemplar-based class-incremental learning (CIL) finetunes the model with all samples of
new classes but few-shot exemplars of old classes in each incremental phase, where the" …
new classes but few-shot exemplars of old classes in each incremental phase, where the" …
Self-growing binary activation network: A novel deep learning model with dynamic architecture
Z Zhang, Y Chen, C Zhou - IEEE Transactions on Neural …, 2022 - ieeexplore.ieee.org
For a deep learning model, the network architecture is crucial as a model with inappropriate
architecture often suffers from performance degradation or parameter redundancy. However …
architecture often suffers from performance degradation or parameter redundancy. However …
SATHUR: Self Augmenting Task Hallucinal Unified Representation for Generalized Class Incremental Learning
S Kanagarajah, T Ambegoda… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Class Incremental Learning (CIL) is inspired by the human ability to learn new
classes without forgetting previous ones. CIL becomes more challenging in real-world …
classes without forgetting previous ones. CIL becomes more challenging in real-world …
Advisil-a class-incremental learning advisor
Recent class-incremental learning methods combine deep neural architectures and learning
algorithms to handle streaming data under memory and computational constraints. The …
algorithms to handle streaming data under memory and computational constraints. The …
Incremental learning with differentiable architecture and forgetting search
As progress is made on training machine learning models on incrementally expanding
classification tasks (ie, incremental learning), a next step is to translate this progress to …
classification tasks (ie, incremental learning), a next step is to translate this progress to …
Exploring the Intersection between Neural Architecture Search and Continual Learning
Despite the significant advances achieved in Artificial Neural Networks (ANNs), their design
process remains notoriously tedious, depending primarily on intuition, experience and trial …
process remains notoriously tedious, depending primarily on intuition, experience and trial …