61 citations · 186 across the 19 of their papers we have counts for
20 papers
On the Status of Foundation Models for SAR Imagery
Nathan Inkawhich
In this work we investigate the viability of foundational AI/ML models for Synthetic Aperture Radar (SAR) object recognition tasks. We are inspired by the tremendous progress being…
Multi-layer Radial Basis Function Networks for Out-of-distribution Detection
Amol Khanna, Chenyi Ling, Derek Everett +2
Existing methods for out-of-distribution (OOD) detection use various techniques to produce a score, separate from classification, that determines how ``OOD'' an input is. Our insig…
OSR-ViT: A Simple and Modular Framework for Open-Set Object Detection and Discovery
Matthew Inkawhich, Nathan Inkawhich, Hao Yang +3
An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work i…
SoK: A Review of Differentially Private Linear Models For High-Dimensional Data
Amol Khanna, Edward Raff, Nathan Inkawhich
Linear models are ubiquitous in data science, but are particularly prone to overfitting and data memorization in high dimensions. To guarantee the privacy of training data, differe…
Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble
Chenhui Xu, Fuxun Yu, Zirui Xu +2
Recent research underscores the pivotal role of the Out-of-Distribution (OOD) feature representation field scale in determining the efficacy of models in OOD detection. Consequentl…
Comprehensive OOD Detection Improvements
Anish Lakkapragada, Amol Khanna, Edward Raff +1
As machine learning becomes increasingly prevalent in impactful decisions, recognizing when inference data is outside the model's expected input distribution is paramount for givin…
Adversarial Attacks on Foundational Vision Models
Nathan Inkawhich, Gwendolyn McDonald, Ryan Luley
Rapid progress is being made in developing large, pretrained, task-agnostic foundational vision models such as CLIP, ALIGN, DINOv2, etc. In fact, we are approaching the point where…
Establishing baselines and introducing TernaryMixOE for fine-grained out-of-distribution detection
Noah Fleischmann, Walter Bennette, Nathan Inkawhich
Machine learning models deployed in the open world may encounter observations that they were not trained to recognize, and they risk misclassifying such observations with high conf…
SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection
Jingyang Zhang, Nathan Inkawhich, Randolph Linderman +3
Building up reliable Out-of-Distribution (OOD) detectors is challenging, often requiring the use of OOD data during training. In this work, we develop a data-driven approach which…
A Global Model Approach to Robust Few-Shot SAR Automatic Target Recognition
Nathan Inkawhich
In real-world scenarios, it may not always be possible to collect hundreds of labeled samples per class for training deep learning-based SAR Automatic Target Recognition (ATR) mode…
Fine-grain Inference on Out-of-Distribution Data with Hierarchical Classification
Randolph Linderman, Jingyang Zhang, Nathan Inkawhich +2
Machine learning methods must be trusted to make appropriate decisions in real-world environments, even when faced with out-of-distribution (OOD) samples. Many current approaches s…
Tunable Hybrid Proposal Networks for the Open World
Matthew Inkawhich, Nathan Inkawhich, Hai Li +1
Current state-of-the-art object proposal networks are trained with a closed-world assumption, meaning they learn to only detect objects of the training classes. These models fail t…
NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
Jerrick Liu, Nathan Inkawhich, Oliver Nina +30
In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR. This challenge is comp…
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments
Jingyang Zhang, Nathan Inkawhich, Randolph Linderman +2
Many real-world scenarios in which DNN-based recognition systems are deployed have inherently fine-grained attributes (e.g., bird-species recognition, medical image classification)…
Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?
Nathan Inkawhich, Kevin J Liang, Jingyang Zhang +3
We design blackbox transfer-based targeted adversarial attacks for an environment where the attacker's source model and the target blackbox model may have disjoint label spaces and…
The Untapped Potential of Off-the-Shelf Convolutional Neural Networks
Matthew Inkawhich, Nathan Inkawhich, Eric Davis +2
Over recent years, a myriad of novel convolutional network architectures have been developed to advance state-of-the-art performance on challenging recognition tasks. As computatio…
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
Huanrui Yang, Jingyang Zhang, Hongliang Dong +6
Recent research finds CNN models for image classification demonstrate overlapped adversarial vulnerabilities: adversarial attacks can mislead CNN models with small perturbations, w…
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
Nathan Inkawhich, Kevin J Liang, Binghui Wang +3
We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers. Rather than focusing on crossing decis…
Transferable Perturbations of Deep Feature Distributions
Nathan Inkawhich, Kevin J Liang, Lawrence Carin +1
Almost all current adversarial attacks of CNN classifiers rely on information derived from the output layer of the network. This work presents a new adversarial attack based on the…
Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers
Nathan Inkawhich, Matthew Inkawhich, Yiran Chen +1
The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video d…