paper-with-me

Papers

Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices

2021-05-21 · Mustafa Ayazoglu

Single-Image Super Resolution (SISR) is a classical computer vision problem and it has been studied for over decades. With the recent success of deep learning methods, recent work on SISR focuses solutions with deep learning methodologies and achieves state-of-the-art results. However most of the state-of-the-art SISR methods contain millions of parameters and layers, which limits their practical applications. In this paper, we propose a hardware (Synaptics Dolphin NPU) limitation aware, extremely lightweight quantization robust real-time super resolution network (XLSR). The proposed model's building block is inspired from root modules for Image classification. We successfully applied root modules to SISR problem, further more to make the model uint8 quantization robust we used Clipped ReLU at the last layer of the network and achieved great balance between reconstruction quality and runtime. Furthermore, although the proposed network contains 30x fewer parameters than VDSR its performance surpasses it on Div2K validation set. The network proved itself by winning Mobile AI 2021 Real-Time Single Image Super Resolution Challenge.

📄 PDF Abstract BibTeX arXiv:2105.10288

Code (3)

Rayyan-Akhtar/XLSR pytorch
cxzhou95/XLSR pytorch
quic/aimet-model-zoo pytorch

Tasks

image-classificationImage ClassificationImage Super-ResolutionQuantizationSuper-Resolution

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…

Similar Papers 제목 키워드 기반

SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

2025-12-04 · Wenhua Cheng, Weiwei Zhang, Heng Guo, Haihao Shen 외 arxiv

Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2 bits and even at 4 bits (e.g., MXFP4). We present SignRoundV2, …

PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models

2025-02-18 · Jiaqi Zhao, Miao Zhang, Ming Wang, Yuzhang Shang 외

Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization. Several existing sub 2-bit post-training quantization (PTQ) methods utilize a mix-precision schem…

BinarizationQuantization

Hand Gesture Recognition for Collaborative Robots Using Lightweight Deep Learning in Real-Time Robotic Systems

2025-07-14 · Muhtadin, I Wayan Agus Darmawan, Muhammad Hilmi Rusydiansyah, I Ketut Eddy Purnama 외 arxiv

Direct and natural interaction is essential for intuitive human-robot collaboration, eliminating the need for additional devices such as joysticks, tablets, or wearable sensors. In this paper, we present a lightweight de…

Hand Gesture Recognition

MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation

2020-06-27 · Jun Liu, Qing Li, Rui Cao, Wenming Tang 외

Predicting depth from a single image is an attractive research topic since it provides one more dimension of information to enable machines to better perceive the world. Recently, deep learning has emerged as an effectiv…

CPUDepth EstimationDepth PredictionGPU+4

HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs

2026-01-28 · Guoan Wang, Feiyu Wang, Zongwei Lv, Yikun Zong 외 arxiv

As large language models (LLMs) continue to scale, deployment is increasingly bottlenecked by the memory wall, motivating a shift toward extremely low-bit quantization. However, most quantization-aware training (QAT) met…