Research
Below are selected research projects in Vision, NLP, Machine Learning, Human-Computer Interaction, and their intersections. Feel free to reach out if you have any questions/thoughts (I’m a major contributor, either the first or last/senior author, in most of these projects).
Twitter: @anh_ng8 | Youtube: some videos of my research. Full list of publications on my Google Scholar.
-
PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans
Giang Nguyen, Valerie Chen, Mohammad Reza Taesiri, Anh Totti Nguyen
Links: pdf | code | project page
-
Vision Language Models Are Blind
Pooyan Rahmanzadehgervi*, Logan Bolton*, Mohammad Reza Taesiri, Anh Totti Nguyen
Links: pdf | code | project page
-
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
Thang M. Pham*, Peijie Chen*, Tin Nguyen*, Seunghyun Yoon, Trung Bui, Anh Totti Nguyen
Links: pdf | code | project page
-
GlitchBench: Can large multimodal models detect video game glitches?
Mohammad Reza Taesiri, Tianjun Feng, Cor-Paul Bezemer, Anh Totti Nguyen
Links: pdf | code | project page
-
Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers
Hai Phan, Cindy X. Le, Vu Le, Yihui Le, Anh Totti Nguyen
Links: pdf | code | project page
-
ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
Mohammad Reza Taesiri, Giang Nguyen, Sarra Habchi, Cor-Paul Bezemer, Anh Nguyen
Links: pdf | code | project page
-
gScoreCAM: What objects is CLIP looking at?
Peijie Chen, Qi Li, Saad Biaz, Trung Bui, Anh Nguyen
Links: pdf | code | project page
-
Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
Giang Nguyen*, Mohammad Reza Taesiri*, Anh Nguyen
Links: pdf | code | project page
-
PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search
Thang M. Pham, Seunghyun Yoon, Trung Bui, Anh Nguyen
Links: pdf | code | project page
-
How explainable are adversarially-robust CNNs?
Mehdi Nourelahi, Lars Kotthoff, Peijie Chen, Anh Nguyen
Links: pdf | code | project page
-
DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover’s Distance Improves Out-Of-Distribution Face Identification
Hai Phan, Anh Nguyen
Links: pdf | code | project page
-
Double Trouble: How to not explain a text classifier’s decisions using counterfactuals synthesized by masked language models
Thang M. Pham, Trung Bui, Long Mai, Anh Nguyen
Links: pdf | code | project page
-
Inverting Adversarially Robust Networks for Image Synthesis
Renan A. Rojas-Gomez, Raymond A. Yeh, Minh N. Do, Anh Nguyen
Links: pdf | code | project page
-
The effectiveness of feature attribution methods and its correlation with automatic evaluation scores
Giang Nguyen, Daeyoung Kim, Anh Nguyen
Links: pdf | code | project page
-
baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling
Michael Alcorn, Anh Nguyen
Links: pdf | code | project page
-
Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?
Thang M. Pham, Trung Bui, Long Mai, Anh Nguyen
Links: pdf | code | project page
-
The shape and simplicity biases of adversarially robust ImageNet-trained CNNs
Peijie Chen*, Chirag Agarwal*, Anh Nguyen*
Links: pdf | code | project page
-
SAM: The Sensitivity of Attribution Methods to Hyperparameters
Naman Bansal*, Chirag Agarwal*, Anh Nguyen*
Links: pdf | code | project page
-
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
Qi Li, Long Mai, Michael A. Alcorn, Anh Nguyen
Links: pdf | code | project page
-
Explaining image classifiers by removing input features using generative models
Chirag Agarwal, Anh Nguyen
Links: pdf | code | project page
-
Strike (with) a Pose: Neural networks are easily fooled by strange poses of familiar objects
Michael Alcorn, Qi Li, Zhitao Gong, Chengfei Wang, Long Mai, Wei-shinn Ku, Anh Nguyen
Links: pdf | code | project page
-
Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
Mohammad S. Norouzzadeh, Anh Nguyen, Margaret Kosmala, Alexandra Swanson, Meredith S. Palmer, Craig Packer, and Jeff Clune
Links: pdf | code | project page
-
VectorDefense: Vectorization as a Defense to Adversarial Examples
Vishaal M. Kabilan, Brandon Morris, Anh Nguyen
Links: pdf | code | project page
-
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
Anh Nguyen, Jeff Clune, Yoshua Bengio, Alexey Dosovitskiy, Jason Yosinski
Links: pdf | code | project page
-
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
Anh Nguyen, Alexey Dosovitskiy, Jason Yosinski, Thomas Brox, Jeff Clune
Links: pdf | code | project page
-
Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
Anh Nguyen, Jason Yosinski, Jeff Clune
Links: pdf | code | project page
-
Deep Neural Network are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Anh Nguyen, Jason Yosinski, Jeff Clune
Links: pdf | code | project page
-
Innovation Engine: Automated Creativity and Improving Stochastic Optimization via Deep Learning
Anh Nguyen, Jason Yosinski, Jeff Clune
Links: pdf | code | project page
-
Understanding Neural Networks Through Deep Visualization
Jason Yosinski, Jeff Clune, Anh Nguyen, Thomas Fuchs, and Hod Lipson
Links: pdf | code | project page
-
3DTouch: A Wearable 3D Input Device for 3D Applications
Anh Nguyen, Amy Banic
Links: pdf | code | project page