A Cosine Similarity-based Method for Out-of-Distribution Detection

1 code implementation • 23 Jun 2023 • Nguyen Ngoc-Hieu, Nguyen Hung-Quang, The-Anh Ta, Thanh Nguyen-Tang, Khoa D Doan, Hoang Thanh-Tung

The ability to detect OOD data is a crucial aspect of practical machine learning applications.

Out-of-Distribution Detection

Class based Influence Functions for Error Detection

1 code implementation • 2 May 2023 • Thang Nguyen-Duc, Hoang Thanh-Tung, Quan Hung Tran, Dang Huu-Tien, Hieu Ngoc Nguyen, Anh T. V. Dau, Nghi D. Q. Bui

Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets.

Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code Corpora

no code implementations • 25 May 2022 • Anh T. V. Dau, Thang Nguyen-Duc, Hoang Thanh-Tung, Nghi D. Q. Bui

Despite the recent trend of developing and applying neural source code models to software engineering tasks, the quality of such models is insufficient for real-world use.

Code Classification Representation Learning

Toward a Generalization Metric for Deep Generative Models

1 code implementation • NeurIPS Workshop ICBINB 2020 • Hoang Thanh-Tung, Truyen Tran

In this paper, we investigate the capacity of these metrics in measuring the generalization capacity.

Memorization

Improving Generalization and Stability of Generative Adversarial Networks

1 code implementation • ICLR 2019 • Hoang Thanh-Tung, Truyen Tran, Svetha Venkatesh

We propose a zero-centered gradient penalty for improving the generalization of the discriminator by pushing it toward the optimal discriminator.

On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks

1 code implementation • 11 Jul 2018 • Hoang Thanh-Tung, Truyen Tran

We show that GAN training is a continual learning problem in which the sequence of changing model distributions is the sequence of tasks to the discriminator.

Continual Learning