Search Results for author: Sang Min Park

Found 2 papers, 0 papers with code

D-Score: A Synapse-Inspired Approach for Filter Pruning

no code implementations8 Aug 2023 Doyoung Park, Jinsoo Kim, Jina Nam, Jooyoung Chang, Sang Min Park

This paper introduces a new aspect for determining the rank of the unimportant filters for filter pruning on convolutional neural networks (CNNs).

Generalized Supervised Contrastive Learning

no code implementations1 Jun 2022 Jaewon Kim, Hyukjong Lee, Jooyoung Chang, Sang Min Park

When applied to ResNet50 with the Momentum Contrast technique, GenSCL achieves a top-1 accuracy of 77. 3% on ImageNet, a 4. 1% relative improvement over traditional supervised contrastive learning.

Contrastive Learning Knowledge Distillation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.