.png){kind=icon}
返回
Mixed-Precision Network Quantization for Infrared Small Target Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2023.3346904.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Network quantization is leveraged to reduce the model size, memory footprint, and computational cost of deep neural networks. It is achieved by representing float weights and activations with lower bit counterparts, which is essential for model deployment on resource-limited devices. However, due to the extremely small size of infrared small targets in the feature map, low-bit quantization could lead to huge information loss of small targets and thus causes severe segmentation performance degradation. To achieve low-bit quantization while maintaining the segmentation performance, we first study the quantization sensitivity of small target segmentation network and observe the sensitivity heterogeneity of different layers in the network. Specifically, feature maps in shallow layers and encoder subnetwork are more vulnerable to information loss caused by quantization as compared to deep layers and decoder subnetwork. Based on these observations, we are motivated to assign a different bitwidth for each block according to their quantization sensitivity. A simple yet effective symmetrically progressive decreasing mixed-precision quantization (SPMix-Q) method is proposed to achieve high-performance segmentation under low-bit quantization (i.e., 2.42 bits for weights and 3.82 bits for activations). The experimental results show that our SPMix-Q achieves comparable accuracy with only 1/13 model size, 1/4.6 memory footprint, and 1/29 computational cost to the full-precision counterparts. Compared with the homogeneous low-bit quantization methods, our method achieves much better performance in terms of intersection of union (IoU) on the benchmark datasets. Our mobile-system-on-a-chip (SOC) (e.g., Kyrin 980, Snapdragon 660, and Dimensity 800U) deployable android application package (APK) is available at: https://github.com/YeRen123455/SIRST-Quantization-Deployment.
Keyword:
Quantization (signal)
Task analysis
Computational modeling
Sensitivity
Image segmentation
Shape
Computational efficiency
Deep neural networks
infrared small target segmentation
mixed precision
network quantization
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
A Hierarchical Cardiac Rhythm Classification Methodology Based on Electrocardiogram Fiducial Points一种基于心电图基准点的分层心律分类方法
OAAI
OAAI分享收藏Combining Deep Denoiser and Low-rank Priors for Infrared Small Target Detection结合深度去噪和低秩先验的红外小目标检测.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Scale invariant small target detection by optimizing signal-to-clutter ratio in heterogeneous background for infrared search and trackPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容