AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Network

• URL: http://arxiv.org/abs/2408.12293v1
• Date: Thu, 22 Aug 2024 11:06:18 GMT
• Title: AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Network
• Authors: Donghwa Kang, Youngmoon Lee, Eun-Kyu Lee, Brent Kang, Jinkyu Lee, Hyeongboo Baek,
• Abstract summary: AT-SNN is designed to dynamically adjust the number of tokens processed during inference in SNN-based ViTs with direct training. We show the effectiveness of AT-SNN in achieving high energy efficiency and accuracy compared to state-of-the-art approaches on the image classification tasks.
• Score: 4.525951256256855
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the training and inference of spiking neural networks (SNNs), direct training and lightweight computation methods have been orthogonally developed, aimed at reducing power consumption. However, only a limited number of approaches have applied these two mechanisms simultaneously and failed to fully leverage the advantages of SNN-based vision transformers (ViTs) since they were originally designed for convolutional neural networks (CNNs). In this paper, we propose AT-SNN designed to dynamically adjust the number of tokens processed during inference in SNN-based ViTs with direct training, wherein power consumption is proportional to the number of tokens. We first demonstrate the applicability of adaptive computation time (ACT), previously limited to RNNs and ViTs, to SNN-based ViTs, enhancing it to discard less informative spatial tokens selectively. Also, we propose a new token-merge mechanism that relies on the similarity of tokens, which further reduces the number of tokens while enhancing accuracy. We implement AT-SNN to Spikformer and show the effectiveness of AT-SNN in achieving high energy efficiency and accuracy compared to state-of-the-art approaches on the image classification tasks, CIFAR10, CIFAR-100, and TinyImageNet. For example, our approach uses up to 42.4% fewer tokens than the existing best-performing method on CIFAR-100, while conserving higher accuracy.

Related papers

• Spiking Neural Networks with Dynamic Time Steps for Vision Transformers [10.118436208925413]
  Spiking Neural Networks (SNNs) have emerged as a popular-temporal computing paradigm vision for complex tasks. We propose a novel training framework that dynamically allocates the number of time steps to each ViT module depending on a trainable score. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and ImageNet with different ViT architectures.
  arXiv  Detail & Related papers  (2023-11-28T03:30:43Z)
• Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration [25.37391055865312]
  Spiking Neural Networks (SNNs) have attracted significant attention for their ability to provide extremely energy-efficient machine intelligence. We propose a Neurogenesis Dynamics-inspired Spiking Neural Network training acceleration framework, NDSNN. Our framework is computational efficient and trains a model from scratch with dynamic sparsity without sacrificing model fidelity.
  arXiv  Detail & Related papers  (2023-04-24T15:54:22Z)
• Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation [70.75043144299168]
  Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware. It is a challenge to efficiently train SNNs due to their non-differentiability. We propose the Differentiation on Spike Representation (DSR) method, which could achieve high performance.
  arXiv  Detail & Related papers  (2022-05-01T12:44:49Z)
• Can Deep Neural Networks be Converted to Ultra Low-Latency Spiking Neural Networks? [3.2108350580418166]
  Spiking neural networks (SNNs) operate via binary spikes distributed over time. SOTA training strategies for SNNs involve conversion from a non-spiking deep neural network (DNN) We propose a new training algorithm that accurately captures these distributions, minimizing the error between the DNN and converted SNN.
  arXiv  Detail & Related papers  (2021-12-22T18:47:45Z)
• Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision [64.71260357476602]
  Event-based vision sensors encode local pixel-wise brightness changes in streams of events rather than image frames. Recent progress in object recognition from event-based sensors has come from conversions of deep neural networks. We propose a hybrid architecture for end-to-end training of deep neural networks for event-based pattern recognition and object detection.
  arXiv  Detail & Related papers  (2021-12-06T23:45:58Z)
• Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks [72.81092567651395]
  Sub-bit Neural Networks (SNNs) are a new type of binary quantization design tailored to compress and accelerate BNNs. SNNs are trained with a kernel-aware optimization framework, which exploits binary quantization in the fine-grained convolutional kernel space. Experiments on visual recognition benchmarks and the hardware deployment on FPGA validate the great potentials of SNNs.
  arXiv  Detail & Related papers  (2021-10-18T11:30:29Z)
• Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding [5.725845886457027]
  Spiking Neural Networks (SNNs) provide higher computational efficiency in event driven neuromorphic hardware. SNNs suffer from high inference latency, resulting from inefficient input encoding and training techniques. This paper presents a training framework for low-latency energy-efficient SNNs.
  arXiv  Detail & Related papers  (2021-07-26T06:16:40Z)
• ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training [68.63354877166756]
  ActNN is a memory-efficient training framework that stores randomly quantized activations for back propagation. ActNN reduces the memory footprint of the activation by 12x, and it enables training with a 6.6x to 14x larger batch size.
  arXiv  Detail & Related papers  (2021-04-29T05:50:54Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)
• You Only Spike Once: Improving Energy-Efficient Neuromorphic Inference to ANN-Level Accuracy [51.861168222799186]
  Spiking Neural Networks (SNNs) are a type of neuromorphic, or brain-inspired network. SNNs are sparse, accessing very few weights, and typically only use addition operations instead of the more power-intensive multiply-and-accumulate operations. In this work, we aim to overcome the limitations of TTFS-encoded neuromorphic systems.
  arXiv  Detail & Related papers  (2020-06-03T15:55:53Z)
• Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation [10.972663738092063]
  Spiking Neural Networks (SNNs) operate with asynchronous discrete events (or spikes) We present a computationally-efficient training technique for deep SNNs. We achieve top-1 accuracy of 65.19% for ImageNet dataset on SNN with 250 time steps, which is 10X faster compared to converted SNNs with similar accuracy.
  arXiv  Detail & Related papers  (2020-05-04T19:30:43Z)

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.