Multi-Precision Quantized Neural Networks via Encoding Decomposition of {-1,+1}

Authors: Qigong Sun, Fanhua Shang, Kang Yang, Xiufang Li, Yan Ren, Licheng Jiao5024-5032

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate the effectiveness of our method on both large-scale image classification tasks (e.g., Image Net) and object detection tasks. In particular, our method with lowbit encoding can still achieve almost the same performance as its full-precision counterparts.
Researcher Affiliation Academia Qigong Sun, Fanhua Shang, Kang Yang, Xiufang Li, Yan Ren, Licheng Jiao Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi an, Shaanxi Province, 710071, China
Pseudocode No The paper includes mathematical equations and diagrams to explain the method but does not provide any explicitly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code No The paper does not contain any statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets Yes We validate the effectiveness of our method on both large-scale image classification tasks (e.g., Image Net) and object detection tasks. ... CIFAR-10 is an image classification benchmark dataset... Image Net ILSVRC-2012 dataset (Russakovsky et al. 2015)... our model is trained on the VOC2007 and VOC2012 train/val set...
Dataset Splits Yes CIFAR-10 is an image classification benchmark dataset, which has 50000 training images and 10000 testing images. ... This dataset consists of 1K categories images, and has over 1.2M images in the training set and 50K images in the validation set. ... our model is trained on the VOC2007 and VOC2012 train/val set, and tested on the VOC2007 test set.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU model, CPU type, memory) used to run the experiments.
Software Dependencies No The paper mentions using 'Adam' and 'stochastic gradient descent (SGD)' for optimization, and 'HTanh' and 'HRe LU' as activation functions. However, it does not specify version numbers for these or any other software components (e.g., Python, PyTorch, TensorFlow).
Experiment Setup Yes We use HTanh( ) as the activation function and employ Adam to optimize all parameters of the network. ... Note that we use SGD to optimize parameters when encoding bit is not less than 3, and the learning rate is set to 0.1. ...the full-precision model parameters activated by Re LU( ) can be directly used as initialization parameters for our 8-bit quantized network.