Search Results for author: Giang Nguyen

Found 15 papers, 9 papers with code

Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation

1 code implementation27 Oct 2023 Son Nguyen, Mikel Lainsa, Hung Dao, Daeyoung Kim, Giang Nguyen

Given the modest size of the dataset and the highly deformable nature of the objects to be segmented, this challenge demands the application of robust data augmentation techniques and wisely-chosen deep learning architectures.

Data Augmentation Instance Segmentation +2

AdvisingNets: Learning to Distinguish Correct and Wrong Classifications via Nearest-Neighbor Explanations

no code implementations25 Aug 2023 Giang Nguyen, Valerie Chen, Anh Nguyen

Besides providing insights into how an image classifier makes its predictions, nearest-neighbor examples also help humans make more accurate decisions.

Image Classification

Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML

2 code implementations15 Jun 2023 Giang Nguyen, Sumon Biswas, Hridesh Rajan

In order to demonstrate the effectiveness of our approach, we evaluated our approach on four fairness problems and 16 different ML models, and our results show a significant improvement over the baseline and existing bias mitigation techniques.

AutoML Decision Making +1

Semi-supervised Neural Machine Translation with Consistency Regularization for Low-Resource Languages

no code implementations2 Apr 2023 Viet H. Pham, Thang M. Pham, Giang Nguyen, Long Nguyen, Dien Dinh

We also introduce a SentenceBERT-based filter to enhance the quality of augmenting data by retaining semantically similar sentence pairs.

Machine Translation NMT +2

Overcoming Catastrophic Forgetting by XAI

no code implementations25 Nov 2022 Giang Nguyen

Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life.

Continual Learning Explainable Artificial Intelligence (XAI) +1

Visual correspondence-based explanations improve AI robustness and human-AI team accuracy

1 code implementation26 Jul 2022 Giang Nguyen, Mohammad Reza Taesiri, Anh Nguyen

Via a large-scale, human study on ImageNet and CUB, our correspondence-based explanations are found to be more useful to users than kNN explanations.

Image Classification

Manas: Mining Software Repositories to Assist AutoML

2 code implementations6 Dec 2021 Giang Nguyen, Md Johir Islam, Rangeet Pan, Hridesh Rajan

Recent work on AutoML, more precisely neural architecture search (NAS), embodied by tools like Auto-Keras aims to solve this problem by essentially viewing it as a search problem where the starting point is a default CNN model, and mutation of this CNN model allows exploration of the space of CNN models to find a CNN model that will work best for the problem.

Image Classification Neural Architecture Search

IRMAC: Interpretable Refined Motifs in Binary Classification for Smart Grid Applications

no code implementations23 Sep 2021 Rui Yuan, S. Ali Pourmousavi, Wen L. Soong, Giang Nguyen, Jon A. R. Liisberg

In this paper, we seek to identify residential consumers based on their BTM equipment, mainly rooftop photovoltaic (PV) systems and electric heating, using imported/purchased energy data from utility meters.

Binary Classification Classification +3

The effectiveness of feature attribution methods and its correlation with automatic evaluation scores

1 code implementation NeurIPS 2021 Giang Nguyen, Daeyoung Kim, Anh Nguyen

Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications.

Explaining How Deep Neural Networks Forget by Deep Visualization

2 code implementations3 May 2020 Giang Nguyen, Shuan Chen, Tae Joon Jun, Daeyoung Kim

Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life.

Continual Learning Explainable artificial intelligence +1

Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization

1 code implementation6 Jan 2020 Giang Nguyen, Shuan Chen, Thao Do, Tae Joon Jun, Ho-Jin Choi, Daeyoung Kim

Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life.

Continual Learning

ContCap: A scalable framework for continual image captioning

1 code implementation19 Sep 2019 Giang Nguyen, Tae Joon Jun, Trung Tran, Tolcha Yalew, Daeyoung Kim

After proving forgetting in image captioning, we propose various techniques to overcome the forgetting dilemma by taking a simple fine-tuning schema as the baseline.

Continual Learning Image Captioning +1

Estimation of Markovian-regime-switching models with independent regimes

1 code implementation19 Jun 2019 Nigel Bean, Angus Lewis, Giang Nguyen

Markovian-regime-switching (MRS) models are commonly used for modelling economic time series, including electricity prices where independent regime models are used, since they can more accurately and succinctly capture electricity price dynamics than dependent regime MRS models can.

Methodology 62F10

A Comprehensive Study on Deep Learning Bug Characteristics

no code implementations3 Jun 2019 Md Johirul Islam, Giang Nguyen, Rangeet Pan, Hridesh Rajan

The key findings of our study include: data bug and logic bug are the most severe bug types in deep learning software appearing more than 48% of the times, major root causes of these bugs are Incorrect Model Parameter (IPS) and Structural Inefficiency (SI) showing up more than 43% of the times.

Dynamic Node Embeddings from Edge Streams

no code implementations12 Apr 2019 John Boaz Lee, Giang Nguyen, Ryan A. Rossi, Nesreen K. Ahmed, Eunyee Koh, Sungchul Kim

In this work, we propose using the notion of temporal walks for learning dynamic embeddings from temporal networks.

Representation Learning valid

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