arXiv cs.AI
· Papers
Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits
arXiv:2607.22564v1 Announce Type: new Abstract: Convolutional neural networks often contain redundant feature maps that increase storage and inference cost. This paper presents a loss-aware feature-map pruning framework using multi-armed bandits. Feature-map pruning is structured because it removes complete convolution