1 code implementation • 12 Nov 2023 • Tianyi Zhang, Shangqing Lyu, Yanli Lei, Sicheng Chen, Nan Ying, Yufang He, Yu Zhao, Yunlu Feng, Hwee Kuan Lee, Guanglei Zhang
Pathological image analysis is a crucial field in computer vision.
no code implementations • 10 May 2023 • Jiyi Zhang, Han Fang, Hwee Kuan Lee, Ee-Chien Chang
Our goal is to select a set of samples from the corpus for the given model.
no code implementations • 2 Jun 2022 • Zerui Chen, Sonia Xhyn Teo, Andrie Ochtman, Shier Nee Saw, Nicholas Cheng, Eric Tien Siang Lim, Murphy Lyu, Hwee Kuan Lee
From our findings, the CNN-LSTM model achieved an accuracy of 81% for the balanced dataset.
1 code implementation • 24 Jan 2022 • Mahsa Paknezhad, Hamsawardhini Rengarajan, Chenghao Yuan, Sujanya Suresh, Manas Gupta, Savitha Ramasamy, Hwee Kuan Lee
Each subset consists of network segments, that can be combined and shared across specific tasks.
no code implementations • 29 Sep 2021 • Davide Coppola, Hwee Kuan Lee, Cuntai Guan
Experiments on the CIFAR10 dataset showed that using only $10\%$ of the full training set, the proposed method was able to adequately defend the model against the AutoPGD attack while maintaining a classification accuracy on clean images outperforming the model with adversarial training by $7\%$.
no code implementations • 5 Jun 2021 • Suvidha Tripathi, Satish Kumar Singh, Hwee Kuan Lee
However, due to patch-based analysis, most of the current methods fail to exploit the underlying spatial relationship among the patches.
1 code implementation • 1 Mar 2021 • Mahsa Paknezhad, Cuong Phuc Ngo, Amadeus Aristo Winarto, Alistair Cheong, Chuen Yang Beh, Jiayang Wu, Hwee Kuan Lee
We found that models trained using our framework, as well as other regularization methods and adversarial training support our hypothesis of data sparsity and that models trained with these methods learn to have decision boundaries more similar to the aforementioned ideal decision boundary.
no code implementations • 29 Jan 2021 • Chengyang Zhou, Thao Vy Dinh, Heyi Kong, Jonathan Yap, Khung Keong Yeo, Hwee Kuan Lee, Kaicheng Liang
The evaluation of obstructions (stenosis) in coronary arteries is currently done by a physician's visual assessment of coronary angiography video sequences.
no code implementations • 1 Jan 2021 • Mustafa Umit Oner, Jared Marc Song, Hwee Kuan Lee, Wing-Kin Sung
We showed that the performance of different pooling filters are different for different MIL tasks.
no code implementations • 29 Jul 2020 • Yusuke Tomita, Kenta Shiina, Yutaka Okabe, Hwee Kuan Lee
We classify the BKT phase and the paramagnetic phase of the quantum XY model using the machine-learning approach.
no code implementations • 2 Jun 2020 • Mustafa Umit Oner, Jared Marc Song Kye-Jet, Hwee Kuan Lee, Wing-Kin Sung
In this paper, we study the effect of different MIL pooling filters on the performance of MIL models in real world MIL tasks.
no code implementations • ICLR 2020 • Connie Kou, Hwee Kuan Lee, Ee-Chien Chang, Teck Khim Ng
Furthermore, on the adversarial counterparts, with the image transformation, the resulting shapes of the distribution of softmax are similar to the distributions from the clean images.
no code implementations • 5 Mar 2020 • Jiyi Zhang, Ee-Chien Chang, Hwee Kuan Lee
Many machine learning adversarial attacks find adversarial samples of a victim model ${\mathcal M}$ by following the gradient of some attack objective functions, either explicitly or implicitly.
1 code implementation • 28 Feb 2020 • Mahsa Paknezhad, Sheng Yang Michael Loh, Yukti Choudhury, Valerie Koh Cui Koh, TimothyTay Kwang Yong, Hui Shan Tan, Ravindran Kanesvaran, Puay Hoon Tan, John Yuen Shyi Peng, Weimiao Yu, Yongcheng Benjamin Tan, Yong Zhen Loy, Min-Han Tan, Hwee Kuan Lee
Motivation: High resolution 2D whole slide imaging provides rich information about the tissue structure.
no code implementations • 12 Jan 2020 • Kenta Shiina, Hiroyuki Mori, Yutaka Okabe, Hwee Kuan Lee
As an alternative to investigating the thermal average of macroscopic physical quantities, they have used the spin configurations for the classification of the disordered and ordered phases of a phase transition through machine learning.
Statistical Mechanics
no code implementations • 9 Oct 2019 • Malay Singh, Emarene Mationg Kalaw, Wang Jie, Mundher Al-Shabi, Chin Fong Wong, Danilo Medina Giron, Kian-Tai Chong, Maxine Tan, Zeng Zeng, Hwee Kuan Lee
In this paper, we present an annotated cribriform dataset along with analysis of deep learning models and hand-crafted features for cribriform pattern detection in prostate histopathological images.
1 code implementation • ICLR 2020 • Mustafa Umit Oner, Hwee Kuan Lee, Wing-Kin Sung
We have constructed a neural network based $ucc$ classifier and experimentally shown that the clustering performance of our framework with our weakly supervised $ucc$ classifier is comparable to that of fully supervised learning models where labels for all instances are known.
no code implementations • 1 Jun 2019 • Connie Kou, Hwee Kuan Lee, Ee-Chien Chang, Teck Khim Ng
Furthermore, on the adversarial counterparts, with the image transformation, the resulting shapes of the distribution of softmax are similar to the distributions from the clean images.
1 code implementation • 2 Apr 2019 • Cuong Phuc Ngo, Amadeus Aristo Winarto, Connie Kou Khor Li, Sojeong Park, Farhan Akram, Hwee Kuan Lee
However, the traditional GAN loss is not directly aligned with the anomaly detection objective: it encourages the distribution of the generated samples to overlap with the real data and so the resulting discriminator has been found to be ineffective as an anomaly detector.
no code implementations • 1 Jan 2019 • Mundher Al-Shabi, Hwee Kuan Lee, Maxine Tan
Different types of Convolutional Neural Networks (CNNs) have been applied to detect cancerous lung nodules from computed tomography (CT) scans.
Ranked #3 on Lung Nodule Classification on LIDC-IDRI
no code implementations • 5 Nov 2018 • Connie Kou, Hwee Kuan Lee, Jorge Sanz, Teck Khim Ng
However, in Kou et al. (2018) and some other works on distribution regression, there is a lack of comprehensive comparative study on both theoretical basis and generalization abilities of the methods.
no code implementations • 13 Apr 2018 • Connie Kou, Hwee Kuan Lee, Teck Khim Ng
Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces.
no code implementations • 13 Feb 2018 • Jiyi Zhang, Hung Dang, Hwee Kuan Lee, Ee-Chien Chang
We propose a flipped-Adversarial AutoEncoder (FAAE) that simultaneously trains a generative model G that maps an arbitrary latent code distribution to a data distribution and an encoder E that embodies an "inverse mapping" that encodes a data sample into a latent code vector.
no code implementations • ICLR 2018 • Connie Kou, Hwee Kuan Lee, Teck Khim Ng
We introduce our Distribution Regression Network (DRN) which performs regression from input probability distributions to output probability distributions.