Optimal channel selection with discrete QCQP

no code implementations • 24 Feb 2022 • Yeonwoo Jeong, Deokjae Lee, Gaon An, Changyong Son, Hyun Oh Song

We first show the greedy approach of recent channel pruning methods ignores the inherent quadratic coupling between channels in the neighboring layers and cannot safely remove inactive weights during the pruning procedure.

RaScaNet: Learning Tiny Models by Raster-Scanning Images

no code implementations • CVPR 2021 • Jaehyoung Yoo, Dongwook Lee, Changyong Son, Sangil Jung, ByungIn Yoo, Changkyu Choi, Jae-Joon Han, Bohyung Han

RaScaNet reads only a few rows of pixels at a time using a convolutional neural network and then sequentially learns the representation of the whole image using a recurrent neural network.

Binary Classification

Succinct Network Channel and Spatial Pruning via Discrete Variable QCQP

no code implementations • 1 Jan 2021 • Yeonwoo Jeong, Deokjae Lee, Gaon An, Changyong Son, Hyun Oh Song

Reducing the heavy computational cost of large convolutional neural networks is crucial when deploying the networks to resource-constrained environments.

Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss

no code implementations • CVPR 2019 • Sangil Jung, Changyong Son, Seohyung Lee, Jinwoo Son, Youngjun Kwak, Jae-Joon Han, Sung Ju Hwang, Changkyu Choi

We demonstrate the effectiveness of our trainable quantizer on ImageNet dataset with various network architectures such as ResNet-18, -34 and AlexNet, on which it outperforms existing methods to achieve the state-of-the-art accuracy.

Quantization