Structured pruning for deep convolutional neural networks: A survey
The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …
attributed to their deeper and wider architectures, which can come with significant …
[HTML][HTML] Applications and techniques for fast machine learning in science
In this community review report, we discuss applications and techniques for fast machine
learning (ML) in science—the concept of integrating powerful ML methods into the real-time …
learning (ML) in science—the concept of integrating powerful ML methods into the real-time …
A survey of quantization methods for efficient neural network inference
This chapter provides approaches to the problem of quantizing the numerical values in deep
Neural Network computations, covering the advantages/disadvantages of current methods …
Neural Network computations, covering the advantages/disadvantages of current methods …
Hrank: Filter pruning using high-rank feature map
Neural network pruning offers a promising prospect to facilitate deploying deep neural
networks on resource-limited devices. However, existing methods are still challenged by the …
networks on resource-limited devices. However, existing methods are still challenged by the …
Group sparsity: The hinge between filter pruning and decomposition for network compression
In this paper, we analyze two popular network compression techniques, ie filter pruning and
low-rank decomposition, in a unified sense. By simply changing the way the sparsity …
low-rank decomposition, in a unified sense. By simply changing the way the sparsity …
Operation-aware soft channel pruning using differentiable masks
We propose a simple but effective data-driven channel pruning algorithm, which
compresses deep neural networks in a differentiable way by exploiting the characteristics of …
compresses deep neural networks in a differentiable way by exploiting the characteristics of …
Self-regulated feature learning via teacher-free feature distillation
L Li - European Conference on Computer Vision, 2022 - Springer
Abstract Knowledge distillation conditioned on intermediate feature representations always
leads to significant performance improvements. Conventional feature distillation framework …
leads to significant performance improvements. Conventional feature distillation framework …
Towards efficient model compression via learned global ranking
Pruning convolutional filters has demonstrated its effectiveness in compressing ConvNets.
Prior art in filter pruning requires users to specify a target model complexity (eg, model size …
Prior art in filter pruning requires users to specify a target model complexity (eg, model size …
Yolobile: Real-time object detection on mobile devices via compression-compilation co-design
The rapid development and wide utilization of object detection techniques have aroused
attention on both accuracy and speed of object detectors. However, the current state-of-the …
attention on both accuracy and speed of object detectors. However, the current state-of-the …