Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression
This addresses the issue of limited computing resources and memory constraints for real-world deployment of CNNs, representing an incremental improvement over existing filter pruning methods.
The paper tackles the problem of compressing and accelerating convolutional neural networks (CNNs) by proposing a novel filter pruning method based on linear relationships in feature map subspaces, achieving state-of-the-art results after fine-tuning.
While the research on convolutional neural networks (CNNs) is progressing quickly, the real-world deployment of these models is often limited by computing resources and memory constraints. In this paper, we address this issue by proposing a novel filter pruning method to compress and accelerate CNNs. Our work is based on the linear relationship identified in different feature map subspaces via visualization of feature maps. Such linear relationship implies that the information in CNNs is redundant. Our method eliminates the redundancy in convolutional filters by applying subspace clustering to feature maps. In this way, most of the representative information in the network can be retained in each cluster. Therefore, our method provides an effective solution to filter pruning for which most existing methods directly remove filters based on simple heuristics. The proposed method is independent of the network structure, thus it can be adopted by any off-the-shelf deep learning libraries. Experiments on different networks and tasks show that our method outperforms existing techniques before fine-tuning, and achieves the state-of-the-art results after fine-tuning.