A Mixed Quantization Network for Computationally Efficient Mobile
Inverse Tone Mapping
- URL: http://arxiv.org/abs/2203.06504v1
- Date: Sat, 12 Mar 2022 19:40:01 GMT
- Title: A Mixed Quantization Network for Computationally Efficient Mobile
Inverse Tone Mapping
- Authors: Juan Borrego-Carazo, Mete Ozay, Frederik Laboyrie, Paul Wisbey
- Abstract summary: We propose combining efficient operations of deep neural networks with a novel mixed quantization scheme to construct a well-performing but computationally efficient mixed quantization network (MQN)
MQN provides up to 10 times improvement on latency and 25 times improvement on memory consumption.
- Score: 8.277567852741242
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Recovering a high dynamic range (HDR) image from a single low dynamic range
(LDR) image, namely inverse tone mapping (ITM), is challenging due to the lack
of information in over- and under-exposed regions. Current methods focus
exclusively on training high-performing but computationally inefficient ITM
models, which in turn hinder deployment of the ITM models in
resource-constrained environments with limited computing power such as edge and
mobile device applications.
To this end, we propose combining efficient operations of deep neural
networks with a novel mixed quantization scheme to construct a well-performing
but computationally efficient mixed quantization network (MQN) which can
perform single image ITM on mobile platforms. In the ablation studies, we
explore the effect of using different attention mechanisms, quantization
schemes, and loss functions on the performance of MQN in ITM tasks. In the
comparative analyses, ITM models trained using MQN perform on par with the
state-of-the-art methods on benchmark datasets. MQN models provide up to 10
times improvement on latency and 25 times improvement on memory consumption.
Related papers
- DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.
We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.
Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
arXiv Detail & Related papers (2025-02-18T02:37:26Z) - USEFUSE: Utile Stride for Enhanced Performance in Fused Layer Architecture of Deep Neural Networks [0.6435156676256051]
This study presents the Sum-of-Products (SOP) units for convolution, which utilize low-latency left-to-right bit-serial arithmetic.
An effective mechanism detects and skips inefficient convolutions after ReLU layers, minimizing power consumption.
Two designs cater to varied demands: one focuses on minimal response time for mission-critical applications, and another focuses on resource-constrained devices with comparable latency.
arXiv Detail & Related papers (2024-12-18T11:04:58Z) - Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval.
A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.
The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
arXiv Detail & Related papers (2024-12-05T09:41:33Z) - 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) - Reservoir computing for system identification and predictive control with limited data [3.1484174280822845]
We assess the ability of RNN variants to both learn the dynamics of benchmark control systems and serve as surrogate models for model predictive control (MPC)
We find that echo state networks (ESNs) have a variety of benefits over competing architectures, namely reductions in computational complexity, longer valid prediction times, and reductions in cost of the MPC objective function.
arXiv Detail & Related papers (2024-10-23T21:59:07Z) - Up-sampling-only and Adaptive Mesh-based GNN for Simulating Physical Systems [7.384641647468888]
We develop a novel hierarchical Mesh Graph Network, namely UA-MGN, for efficient and effective mechanical simulation.
Evaluation on two synthetic and one real datasets demonstrates the superiority of the UA-MGN.
arXiv Detail & Related papers (2024-09-07T07:09:58Z) - Cross-Scan Mamba with Masked Training for Robust Spectral Imaging [51.557804095896174]
We propose the Cross-Scanning Mamba, named CS-Mamba, that employs a Spatial-Spectral SSM for global-local balanced context encoding.
Experiment results show that our CS-Mamba achieves state-of-the-art performance and the masked training method can better reconstruct smooth features to improve the visual quality.
arXiv Detail & Related papers (2024-08-01T15:14:10Z) - Full-Stack Optimization for CAM-Only DNN Inference [2.0837295518447934]
This paper explores the combination of algorithmic optimizations for ternary weight neural networks and associative processors.
We propose a novel compilation flow to optimize convolutions on APs by reducing their arithmetic intensity.
Our solution improves the energy efficiency of ResNet-18 inference on ImageNet by 7.5x compared to crossbar in-memory accelerators.
arXiv Detail & Related papers (2024-01-23T10:27:38Z) - Collaborative Intelligent Reflecting Surface Networks with Multi-Agent
Reinforcement Learning [63.83425382922157]
Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks.
In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting.
arXiv Detail & Related papers (2022-03-26T20:37:14Z) - Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain.
In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden.
Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
arXiv Detail & Related papers (2021-03-15T12:54:26Z)
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.