相关论文: Survey of Quantization Techniques for On-Device Vi…

The Mamba model, utilizing a structured state-space model (SSM), offers linear time complexity and demonstrates significant potential. Vision Mamba (ViM) extends this framework to vision tasks by incorporating a bidirectional SSM and patch…

Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on…

Deep neural networks have achieved state-of-the art performance on various computer vision tasks. However, their deployment on resource-constrained devices has been hindered due to their high computational and storage complexity. While…

Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-training quantization (PTQ) offers a promising compression…

Low-bit quantization emerges as one of the most promising compression approaches for deploying deep neural networks on edge devices. Mixed-precision quantization leverages a mixture of bit-widths to unleash the accuracy and efficiency…

Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory. In this work, we propose a framework for formally verifying…

State-space models (SSMs) have recently gained attention in deep learning for their ability to efficiently model long-range dependencies, making them promising candidates for edge-AI applications. In this paper, we analyze the effects of…

Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model…

Vision transformer emerges as a potential architecture for vision tasks. However, the intense computation and non-negligible delay hinder its application in the real world. As a widespread model compression technique, existing post-training…

Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ iterative parameter updates to preserve accuracy under high…

Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However, as a large-scale model, the immense memory and computation costs hinder its practical deployment. In this paper, we propose a…

Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…

Albeit the scalable performance of vision transformers (ViTs), the dense computational costs (training & inference) undermine their position in industrial applications. Post-training quantization (PTQ), tuning ViTs with a tiny dataset and…

Deep learning-based Visual SLAM (vSLAM) systems exhibit exceptional geometric reasoning capabilities, yet their prohibitive computational overhead severely restricts deployment on resource-constrained autonomous platforms. This paper…

Deep learning models have shown strong performance in medical image analysis, but deploying them in low-resource clinical environments remains difficult due to computational, memory, and power constraints. This paper presents a…

Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the…

Despite the outstanding performance of transformers in both language and vision tasks, the expanding computation and model size have increased the demand for efficient deployment. To address the heavy computation and parameter drawbacks,…

The development of edge computing places critical demands on energy-efficient model deployment for multiple-input multiple-output (MIMO) detection tasks. Deploying deep unfolding models such as PGD-Nets and ADMM-Nets into…

Hybrid models that combine convolutional and transformer blocks offer strong performance in computer vision (CV) tasks but are resource-intensive for edge deployment. Although post-training quantization (PTQ) can help reduce resource…

Recent one-shot Neural Architecture Search algorithms rely on training a hardware-agnostic super-network tailored to a specific task and then extracting efficient sub-networks for different hardware platforms. Popular approaches separate…