CNN Mixture-of-Depths

• URL: http://arxiv.org/abs/2409.17016v1
• Date: Wed, 25 Sep 2024 15:19:04 GMT
• Title: CNN Mixture-of-Depths
• Authors: Rinor Cakaj, Jens Mehnert, Bin Yang,
• Abstract summary: Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs) We introduce Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs)
• Score: 4.150676163661315
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs), a novel approach that enhances the computational efficiency of CNNs by selectively processing channels based on their relevance to the current prediction. This method optimizes computational resources by dynamically selecting key channels in feature maps for focused processing within the convolutional blocks (Conv-Blocks), while skipping less relevant channels. Unlike conditional computation methods that require dynamic computation graphs, CNN MoD uses a static computation graph with fixed tensor sizes which improve hardware efficiency. It speeds up the training and inference processes without the need for customized CUDA kernels, unique loss functions, or finetuning. CNN MoD either matches the performance of traditional CNNs with reduced inference times, GMACs, and parameters, or exceeds their performance while maintaining similar inference times, GMACs, and parameters. For example, on ImageNet, ResNet86-MoD exceeds the performance of the standard ResNet50 by 0.45% with a 6% speedup on CPU and 5% on GPU. Moreover, ResNet75-MoD achieves the same performance as ResNet50 with a 25% speedup on CPU and 15% on GPU.

Related papers

• SCONNA: A Stochastic Computing Based Optical Accelerator for Ultra-Fast, Energy-Efficient Inference of Integer-Quantized CNNs [0.0]
  A CNN inference task uses convolution operations that are typically transformed into vector-dot-product (VDP) operations. Several photonic microring resonators (MRRs) based hardware architectures have been proposed to accelerate integer-quantized CNNs. Existing photonic MRR-based analog accelerators exhibit a very strong trade-off between the achievable input/weight precision and VDP operation size.
  arXiv  Detail & Related papers  (2023-02-14T13:35:15Z)
• Attention-based Feature Compression for CNN Inference Offloading in Edge Computing [93.67044879636093]
  This paper studies the computational offloading of CNN inference in device-edge co-inference systems. We propose a novel autoencoder-based CNN architecture (AECNN) for effective feature extraction at end-device. Experiments show that AECNN can compress the intermediate data by more than 256x with only about 4% accuracy loss.
  arXiv  Detail & Related papers  (2022-11-24T18:10:01Z)
• EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators [12.223778147172107]
  Dilated and transposed convolutions are widely used in modern convolutional neural networks (CNNs) These kernels stress current compute systems due to their high memory intensity, exascale compute demands, and large energy consumption. We propose EcoFlow, a new set of dataflows and mapping algorithms for dilated and transposed convolutions.
  arXiv  Detail & Related papers  (2022-02-04T18:48:36Z)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• Greedy Network Enlarging [53.319011626986004]
  We propose a greedy network enlarging method based on the reallocation of computations. With step-by-step modifying the computations on different stages, the enlarged network will be equipped with optimal allocation and utilization of MACs. With application of our method on GhostNet, we achieve state-of-the-art 80.9% and 84.3% ImageNet top-1 accuracies.
  arXiv  Detail & Related papers  (2021-07-31T08:36:30Z)
• Content-Aware Convolutional Neural Networks [98.97634685964819]
  Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. We propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1x1 convolutional kernel to replace the original large kernel.
  arXiv  Detail & Related papers  (2021-06-30T03:54:35Z)
• Continual 3D Convolutional Neural Networks for Real-time Processing of Videos [93.73198973454944]
  We introduce Continual 3D Contemporalal Neural Networks (Co3D CNNs) Co3D CNNs process videos frame-by-frame rather than by clip by clip. We show that Co3D CNNs initialised on the weights from preexisting state-of-the-art video recognition models reduce floating point operations for frame-wise computations by 10.0-12.4x while improving accuracy on Kinetics-400 by 2.3-3.8x.
  arXiv  Detail & Related papers  (2021-05-31T18:30:52Z)
• MoViNets: Mobile Video Networks for Efficient Video Recognition [52.49314494202433]
  3D convolutional neural networks (CNNs) are accurate at video recognition but require large computation and memory budgets. We propose a three-step approach to improve computational efficiency while substantially reducing the peak memory usage of 3D CNNs.
  arXiv  Detail & Related papers  (2021-03-21T23:06:38Z)
• PENNI: Pruned Kernel Sharing for Efficient CNN Inference [41.050335599000036]
  State-of-the-art (SOTA) CNNs achieve outstanding performance on various tasks. Their high computation demand and massive number of parameters make it difficult to deploy these SOTA CNNs onto resource-constrained devices. We propose PENNI, a CNN model compression framework that is able to achieve model compactness and hardware efficiency simultaneously.
  arXiv  Detail & Related papers  (2020-05-14T16:57:41Z)
• DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks [16.169176006544436]
  We propose a novel dynamic convolution method to adaptively generate convolution kernels based on image contents. Based on the architecture MobileNetV3-Small/Large, DyNet achieves 70.3/77.1% Top-1 accuracy on ImageNet with an improvement of 2.9/1.9%.
  arXiv  Detail & Related papers  (2020-04-22T16:58:05Z)
• Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs [6.035819238203187]
  We show that a reduction in the number of convolutional channels, pruning 12% of the initial size, is in some cases detrimental to performance. We also find examples where performance-aware pruning achieves the intended results, with performance speedups of 3x with cuDNN and above 10x with Arm Compute Library and TVM.
  arXiv  Detail & Related papers  (2020-02-20T12:07:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.