no code implementations • 18 Apr 2024 • Shijie Fang, Qianhan Feng, Tong Lin
VCC is an universal plugin for SSL confidence calibration, using a variational autoencoder to select more accurate pseudo labels based on three types of consistency scores.
no code implementations • 2 Feb 2023 • Tong Lin, Sijie Chen, Ruchira Basu, Dehu Pei, Xiaolin Cheng, Levent Burak Kara
Despite the prevalence and many successes of deep learning applications in de novo molecular design, the problem of peptide generation targeting specific proteins remains unsolved.
no code implementations • 3 Oct 2022 • Xiaohan Zou, Tong Lin
However, they still suffer from the catastrophic forgetting problem in the setting of continual learning, since the past data of previous tasks are no longer available.
no code implementations • 27 Sep 2022 • Yee-Yang Tee, Deruo Cheng, Chye-Soon Chee, Tong Lin, Yiqiong Shi, Bah-Hwee Gwee
To address the domain shift problem, we propose Histogram-gated Image Translation (HGIT), an unsupervised domain adaptation framework which transforms images from a given source dataset to the domain of a target dataset, and utilize the transformed images for training a segmentation network.
1 code implementation • 11 Aug 2022 • Yucong Liu, Shixing Yu, Tong Lin
In this paper, we develop a novel regularization method for deep neural networks by penalizing the trace of Hessian.
no code implementations • 2 May 2022 • Zijian Ying, Qianmu Li, Zhichao Lian, Jun Hou, Tong Lin, Tao Wang
To organize these excitations into final saliency maps, we introduce a double-chain backpropagation procedure.
no code implementations • 18 Oct 2021 • Ye Ma, Jin Ma, Min Zhou, Quan Chen, Tiezheng Ge, Yuning Jiang, Tong Lin
Secondly, another GAN model is trained to synthesize real images based on the extended semantic layouts.
no code implementations • 21 Aug 2021 • Zhiyi Chen, Tong Lin
In Principal Gradient Direction, we optimize a target gradient that not only represents the major contribution of past gradients, but also retains the new knowledge of the current gradient.
no code implementations • 18 Jul 2021 • Zhou Shao, Tong Lin
Therefore, DecGD gets a rapid convergence in the early phases of training and controls the effective learning rates according to the loss based vectors which help lead to a better generalization.
no code implementations • 20 May 2021 • Shijie Fang, Tong Lin
Moreover, our method is proven to be robust to label noise with experiments on Cifar-10 dataset.
no code implementations • 1 Jan 2021 • Zhou Shao, Tong Lin
Stochastic momentum optimization methods, also known as stochastic heavy ball (SHB) methods, are one of the most popular optimization methods for deep learning.
1 code implementation • 5 Mar 2020 • Zhenguo Nie, Tong Lin, Haoliang Jiang, Levent Burak Kara
In topology optimization using deep learning, load and boundary conditions represented as vectors or sparse matrices often miss the opportunity to encode a rich view of the design problem, leading to less than ideal generalization results.
1 code implementation • NeurIPS 2019 • Jinhao Dong, Tong Lin
The new feature is that the classifier attempts to increase the margin of real examples and to decrease the margin of fake examples.