Search Results for author: Jinlin Xiang

Found 4 papers, 0 papers with code

TKIL: Tangent Kernel Approach for Class Balanced Incremental Learning

no code implementations17 Jun 2022 Jinlin Xiang, Eli Shlizerman

In our work, we propose to address these challenges with the introduction of a novel methodology of Tangent Kernel for Incremental Learning (TKIL) that achieves class-balanced performance.

class-incremental learning Incremental Learning

Incremental Learning Meets Transfer Learning: Application to Multi-site Prostate MRI Segmentation

no code implementations3 Jun 2022 Chenyu You, Jinlin Xiang, Kun Su, Xiaoran Zhang, Siyuan Dong, John Onofrey, Lawrence Staib, James S. Duncan

Many medical datasets have recently been created for medical image segmentation tasks, and it is natural to question whether we can use them to sequentially train a single model that (1) performs better on all these datasets, and (2) generalizes well and transfers better to the unknown target site domain.

Image Segmentation Incremental Learning +3

Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks

no code implementations26 Feb 2021 Jinlin Xiang, Shane Colburn, Arka Majumdar, Eli Shlizerman

However, a major challenge in using this spectral approach, as well as in an optical implementation of CNNs, is the inclusion of a nonlinearity between each convolutional layer, without which CNN performance drops dramatically.

Knowledge Distillation Network Pruning +1

BI-MAML: Balanced Incremental Approach for Meta Learning

no code implementations12 Jun 2020 Yang Zheng, Jinlin Xiang, Kun Su, Eli Shlizerman

The balanced learning strategy enables BI-MAML to both outperform other state-of-the-art models in terms of classification accuracy for existing tasks and also accomplish efficient adaption to similar new tasks with less required shots.

General Classification Image Classification +1

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