1.5k citations · 2.1k across the 26 of their papers we have counts for
28 papers
PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans
Giang, Nguyen, Valerie Chen +2
Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model…
A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation
Ronast Subedi, Rebati Raman Gaire, Sharib Ali +3
This paper presents a solution to the cross-domain adaptation problem for 2D surgical image segmentation, explicitly considering the privacy protection of distributed datasets belo…
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 +2
Image classifiers are information-discarding machines, by design. Yet, how these models discard information remains mysterious. We hypothesize that one way for image classifiers to…
Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
Giang Nguyen, Mohammad Reza Taesiri, Anh Nguyen
Explaining artificial intelligence (AI) predictions is increasingly important and even imperative in many high-stakes applications where humans are the ultimate decision-makers. In…
PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search
Thang M. Pham, Seunghyun Yoon, Trung Bui +1
While contextualized word embeddings have been a de-facto standard, learning contextualized phrase embeddings is less explored and being hindered by the lack of a human-annotated b…
How explainable are adversarially-robust CNNs?
Mehdi Nourelahi, Lars Kotthoff, Peijie Chen +1
Three important criteria of existing convolutional neural networks (CNNs) are (1) test-set accuracy; (2) out-of-distribution accuracy; and (3) explainability. While these criteria…
DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification
Hai Phan, Anh Nguyen
Face identification (FI) is ubiquitous and drives many high-stake decisions made by law enforcement. State-of-the-art FI approaches compare two images by taking the cosine similari…
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 +1
A principle behind dozens of attribution methods is to take the prediction difference between before-and-after an input feature (here, a token) is removed as its attribution. A pop…
The DEformer: An Order-Agnostic Distribution Estimating Transformer
Michael A. Alcorn, Anh Nguyen
Order-agnostic autoregressive distribution (density) estimation (OADE), i.e., autoregressive distribution estimation where the features can occur in an arbitrary order, is a challe…
The effectiveness of feature attribution methods and its correlation with automatic evaluation scores
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. Hundreds of papers have either proposed new…
baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling
Michael A. Alcorn, Anh Nguyen
Multi-agent spatiotemporal modeling is a challenging task from both an algorithmic design and computational complexity perspective. Recent work has explored the efficacy of traditi…
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 +1
Do state-of-the-art natural language understanding models care about word order - one of the most important characteristics of a sequence? Not always! We found 75% to 90% of the co…
The shape and simplicity biases of adversarially robust ImageNet-trained CNNs
Peijie Chen, Chirag Agarwal, Anh Nguyen
Increasingly more similarities between human vision and convolutional neural networks (CNNs) have been revealed in the past few years. Yet, vanilla CNNs often fall short in general…
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 +1
Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities. Specifically, BigGANs a class-conditional Generative Adve…
Explaining image classifiers by removing input features using generative models
Chirag Agarwal, Anh Nguyen
Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e.g. blurring, adding no…
Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
Michael A. Alcorn, Qi Li, Zhitao Gong +4
Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including natural, non-adversarial on…
Improving Adversarial Robustness by Encouraging Discriminative Features
Chirag Agarwal, Anh Nguyen, Dan Schonfeld
Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.…
VectorDefense: Vectorization as a Defense to Adversarial Examples
Vishaal Munusamy Kabilan, Brandon Morris, Anh Nguyen
Training deep neural networks on images represented as grids of pixels has brought to light an interesting phenomenon known as adversarial examples. Inspired by how humans reconstr…
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Joel Lehman, Jeff Clune, Dusan Misevic +50
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them. However, because evolution is an algorithmic pr…
Spatial PixelCNN: Generating Images from Patches
Nader Akoury, Anh Nguyen
In this paper we propose Spatial PixelCNN, a conditional autoregressive model that generates images from small patches. By conditioning on a grid of pixel coordinates and global fe…
3DTouch: Towards a Wearable 3D Input Device for 3D Applications
Anh Nguyen
Three-dimensional (3D) applications have come to every corner of life. We present 3DTouch, a novel 3D wearable input device worn on the fingertip for interacting with 3D applicatio…
Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
Mohammed Sadegh Norouzzadeh, Anh Nguyen, Margaret Kosmala +4
Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would revolutionize our ability to study and conserve ecosystems. We in…
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
Anh Nguyen, Alexey Dosovitskiy, Jason Yosinski +2
Deep neural networks (DNNs) have demonstrated state-of-the-art results on many pattern recognition tasks, especially vision classification problems. Understanding the inner working…
Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
Anh Nguyen, Jason Yosinski, Jeff Clune
We can better understand deep neural networks by identifying which features each of their neurons have learned to detect. To do so, researchers have created Deep Visualization tech…