A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion
- URL: http://arxiv.org/abs/2501.07451v1
- Date: Mon, 13 Jan 2025 16:24:49 GMT
- Title: A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion
- Authors: Fabio Montello, Ronja Güldenring, Simone Scardapane, Lazaros Nalpantidis,
- Abstract summary: We present a survey that synthesizes and unifies existing Dynamic Neural Networks research in the context of Computer Vision.
We argue that Dynamic Neural Networks are particularly beneficial in the context of Sensor Fusion for better adaptivity, noise reduction and information prioritization.
- Score: 7.2631793071417725
- License:
- Abstract: Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neglect the fact that different inputs have different complexities, thus requiring different amount of computations. Dynamic Neural Networks allow to condition the number of computations to the specific input. The current literature on the topic is very extensive and fragmented. We present a comprehensive survey that synthesizes and unifies existing Dynamic Neural Networks research in the context of Computer Vision. Additionally, we provide a logical taxonomy based on which component of the network is adaptive: the output, the computation graph or the input. Furthermore, we argue that Dynamic Neural Networks are particularly beneficial in the context of Sensor Fusion for better adaptivity, noise reduction and information prioritization. We present preliminary works in this direction.
Related papers
- Neuromorphic Wireless Split Computing with Multi-Level Spikes [69.73249913506042]
Neuromorphic computing uses spiking neural networks (SNNs) to perform inference tasks.
embedding a small payload within each spike exchanged between spiking neurons can enhance inference accuracy without increasing energy consumption.
split computing - where an SNN is partitioned across two devices - is a promising solution.
This paper presents the first comprehensive study of a neuromorphic wireless split computing architecture that employs multi-level SNNs.
arXiv Detail & Related papers (2024-11-07T14:08:35Z) - Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
Task-oriented edge computing addresses this by shifting data analysis to the edge.
Existing methods struggle to balance high model performance with low resource consumption.
We propose a novel co-design framework to optimize neural network architecture.
arXiv Detail & Related papers (2024-10-29T19:02:54Z) - Sparsity-Aware Hardware-Software Co-Design of Spiking Neural Networks: An Overview [1.0499611180329804]
Spiking Neural Networks (SNNs) are inspired by the sparse and event-driven nature of biological neural processing, and offer the potential for ultra-low-power artificial intelligence.
We explore the hardware-software co-design of sparse SNNs, examining how sparsity representation, hardware architectures, and training techniques influence hardware efficiency.
Our work aims to illuminate the path towards embedded neuromorphic systems that fully exploit the computational advantages of sparse SNNs.
arXiv Detail & Related papers (2024-08-26T17:22:11Z) - An Attempt to Devise a Pairwise Ising-Type Maximum Entropy Model Integrated Cost Function for Optimizing SNN Deployment [0.0]
A spiking neural network (SNN) deployment process often involves partitioning the neural network onto processing units within the neuromorphic hardware.
Finding optimal deployment schemes is an NP-hard problem.
These objectives require consideration of network dynamics shaped by neuron activity patterns.
Our approach focuses on network dynamics, which are hardware-independent and can be modeled separately from specific hardware configurations.
arXiv Detail & Related papers (2024-07-09T16:33:43Z) - Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
We propose to represent neural networks as computational graphs of parameters.
Our approach enables a single model to encode neural computational graphs with diverse architectures.
We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
arXiv Detail & Related papers (2024-03-18T18:01:01Z) - Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems [9.382423715831687]
In this paper, we back to the classical network structure and prove that the vanilla feedforward networks could also be a numerical discretization of dynamic systems.
Our results could provide a new perspective for understanding the approximation properties of feedforward neural networks.
arXiv Detail & Related papers (2022-09-22T10:32:08Z) - Deep Neural Networks as Complex Networks [1.704936863091649]
We use Complex Network Theory to represent Deep Neural Networks (DNNs) as directed weighted graphs.
We introduce metrics to study DNNs as dynamical systems, with a granularity that spans from weights to layers, including neurons.
We show that our metrics discriminate low vs. high performing networks.
arXiv Detail & Related papers (2022-09-12T16:26:04Z) - Dynamic Inference with Neural Interpreters [72.90231306252007]
We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules.
inputs to the model are routed through a sequence of functions in a way that is end-to-end learned.
We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
arXiv Detail & Related papers (2021-10-12T23:22:45Z) - On the role of feedback in visual processing: a predictive coding
perspective [0.6193838300896449]
We consider deep convolutional networks (CNNs) as models of feed-forward visual processing and implement Predictive Coding (PC) dynamics.
We find that the network increasingly relies on top-down predictions as the noise level increases.
In addition, the accuracy of the network implementing PC dynamics significantly increases over time-steps, compared to its equivalent forward network.
arXiv Detail & Related papers (2021-06-08T10:07:23Z) - Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths.
Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
arXiv Detail & Related papers (2020-10-02T16:50:26Z) - Spiking Neural Networks Hardware Implementations and Challenges: a
Survey [53.429871539789445]
Spiking Neural Networks are cognitive algorithms mimicking neuron and synapse operational principles.
We present the state of the art of hardware implementations of spiking neural networks.
We discuss the strategies employed to leverage the characteristics of these event-driven algorithms at the hardware level.
arXiv Detail & Related papers (2020-05-04T13:24:00Z)
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.