DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge

• URL: http://arxiv.org/abs/2603.17275v1
• Date: Wed, 18 Mar 2026 01:57:21 GMT
• Title: DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge
• Abstract summary: We propose DANCE, a fine-grained, input-aware, dynamic pruning framework for 3D CNNs.<n>Our method achieves substantial savings in multiply-accumulate (MAC) operations and memory accesses.<n> Hardware validation on the NVIDIA Jetson Nano GPU and the Qualcomm Snapdragon 8 Gen 1 platform demonstrates respective speedups of 1.37X and 2.22X.
• Score: 0.5964436882344727
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail to adapt to the computational complexity of input samples in a dynamic manner to minimize energy consumption. In this research, we propose DANCE, a fine-grained, input-aware, dynamic pruning framework for 3D CNNs to maximize power efficiency with negligible to zero impact on performance. In the proposed two-step approach, the first step is called activation variability amplification (AVA), and the 3D CNN model is retrained to increase the variance of the magnitude of neuron activations across the network in this step, facilitating pruning decisions across diverse CNN input scenarios. In the second step, called adaptive activation pruning (AAP), a lightweight activation controller network is trained to dynamically prune frames, channels, and features of 3D convolutional layers of the network (different for each layer), based on statistics of the outputs of the first layer of the network. Our method achieves substantial savings in multiply-accumulate (MAC) operations and memory accesses by introducing sparsity within convolutional layers. Hardware validation on the NVIDIA Jetson Nano GPU and the Qualcomm Snapdragon 8 Gen 1 platform demonstrates respective speedups of 1.37X and 2.22X, achieving up to 1.47X higher energy efficiency compared to the state of the art.

Related papers

• Rapid Salient Object Detection with Difference Convolutional Neural Networks [49.838283141381716]
  This paper addresses the challenge of deploying salient object detection (SOD) on resource-constrained devices with real-time performance.<n>We propose an efficient network design that combines traditional wisdom on SOD and the representation power of modern CNNs.
  arXiv  Detail & Related papers  (2025-07-01T20:41:05Z)
• An Efficient 3D Convolutional Neural Network with Channel-wise, Spatial-grouped, and Temporal Convolutions [3.798710743290466]
  We introduce a simple and very efficient 3D convolutional neural network for video action recognition.<n>We evaluate the performance and efficiency of our proposed network on several video action recognition datasets.
  arXiv  Detail & Related papers  (2025-03-02T08:47:06Z)
• Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Network [1.5215973379400674]
  Spiking Neural Networks (SNNs) are seen as an energy-efficient alternative to traditional Artificial Neural Networks (ANNs)<n>We present a unified training-free conversion framework that significantly enhances both the performance and efficiency of converted SNNs.
  arXiv  Detail & Related papers  (2024-12-18T09:38:54Z)
• Kolmogorov-Arnold Transformer [72.88137795439407]
  We introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces layers with Kolmogorov-Arnold Network (KAN) layers. We identify three key challenges: (C1) Base function, (C2) Inefficiency, and (C3) Weight. With these designs, KAT outperforms traditional-based transformers.
  arXiv  Detail & Related papers  (2024-09-16T17:54:51Z)
• Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators [0.20971479389679332]
  Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors.<n>We show that enabling rich mixed quantization schemes during the implementation can open a previously hidden space of mappings.<n>CNNs utilizing quantized weights and activations and suitable mappings can significantly improve trade-offs among the accuracy, energy, and memory requirements.
  arXiv  Detail & Related papers  (2024-04-08T10:10:30Z)
• Ev-Edge: Efficient Execution of Event-based Vision Algorithms on Commodity Edge Platforms [10.104371980353973]
  Ev-Edge is a framework that contains three key optimizations to boost the performance of event-based vision systems on edge platforms. On several state-of-art networks for a range of autonomous navigation tasks, Ev-Edge achieves 1.28x-2.05x improvements in latency and 1.23x-2.15x in energy.
  arXiv  Detail & Related papers  (2024-03-23T04:44:55Z)
• Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance [1.52292571922932]
  We present a new approach to receptive field analysis that can yield these types of theoretical and empirical performance gains. Our approach is able to improve ImageNet1K performance across a wide range of well-known, state-of-the-art (SOTA) model classes.
  arXiv  Detail & Related papers  (2022-11-26T05:27:44Z)
• Dynamics-aware Adversarial Attack of Adaptive Neural Networks [75.50214601278455]
  We investigate the dynamics-aware adversarial attack problem of adaptive neural networks. We propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient. Our LGM achieves impressive adversarial attack performance compared with the dynamic-unaware attack methods.
  arXiv  Detail & Related papers  (2022-10-15T01:32:08Z)
• 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)
• MicroNet: Towards Image Recognition with Extremely Low FLOPs [117.96848315180407]
  MicroNet is an efficient convolutional neural network using extremely low computational cost. A family of MicroNets achieve a significant performance gain over the state-of-the-art in the low FLOP regime. For instance, MicroNet-M1 achieves 61.1% top-1 accuracy on ImageNet classification with 12 MFLOPs, outperforming MobileNetV3 by 11.3%.
  arXiv  Detail & Related papers  (2020-11-24T18:59:39Z)
• RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices [57.877112704841366]
  This paper proposes RT3D, a model compression and mobile acceleration framework for 3D CNNs. For the first time, real-time execution of 3D CNNs is achieved on off-the-shelf mobiles.
  arXiv  Detail & Related papers  (2020-07-20T02:05:32Z)

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.