.png){kind=icon}
返回
GradQuant: Low-Loss Quantization for Remote-Sensing Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2023.3308582.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional neural network-based methods have shown remarkable performance in remote-sensing object detection. However, their deployment on resource-limited embedded devices is hindered by their high computational complexity. Neural network quantization methods have been proven effective in compressing and accelerating CNN models by clipping outlier activations and utilizing low-precision values to represent weights and clipped activations. Nonetheless, the clipping of outlier activations leads to distortion of object local features. Furthermore, the lack of enhanced overall feature mining exacerbates the degradation of detection accuracy. To address the limitations above, we propose an innovative clipping-free quantization method called GradQuant, which mitigates the model's quantization accuracy loss caused by clipping outlier activations and the lack of overall feature mining. Specifically, a bounded activation function (sigmoid-weighted tanh, SiTanh) is carefully designed to ensure that object features are represented within a limited range without clipping. On the basis of this, an activation substitution training (AST) method is codesigned to prompt models to focus more on nonoutlier object features instead of outlier-like local ones. Extensive experiments on public remote-sensing datasets demonstrate the effectiveness of the GradQuant method compared with other state-of-the-art quantization methods.
Keyword:
Quantization (signal)
Training
Remote sensing
Feature extraction
Object detection
Neural networks
Numerical models
Activation function
clipping distortion
neural network quantization
object detection
remote-sensing images
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
引用论文
.png){kind=icon}
分享收藏分享收藏Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural Networks基于卷积神经网络的遥感图像目标精确定位
OAAI
OAAI分享收藏
查看更多内容