56 citations · 163 across the 22 of their papers we have counts for
23 papers
Visual Variational Autoencoder Prompt Tuning
Xi Xiao, Yunbei Zhang, Yanshuh Li +5
Parameter-efficient fine-tuning (PEFT) has emerged as a crucial approach for adapting large vision transformers to downstream tasks without the prohibitive computational costs of f…
OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation
Yunbei Zhang, Akshay Mehra, Jihun Hamm
Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous meth…
DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
Yunbei Zhang, Akshay Mehra, Shuaicheng Niu +1
Continual Test-Time Adaptation (CTTA) seeks to adapt source pre-trained models to continually changing, unseen target domains. While existing CTTA methods assume structured domain…
Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport
Akshay Mehra, Yunbei Zhang, Jihun Hamm
Gauging the performance of ML models on data from unseen domains at test-time is essential yet a challenging problem due to the lack of labels in this setting. Moreover, the perfor…
On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization
Akshay Mehra, Yunbei Zhang, Bhavya Kailkhura +1
Achieving high accuracy on data from domains unseen during training is a fundamental challenge in domain generalization (DG). While state-of-the-art DG classifiers have demonstrate…
Achieving Reliable and Fair Skin Lesion Diagnosis via Unsupervised Domain Adaptation
Janet Wang, Yunbei Zhang, Zhengming Ding +1
The development of reliable and fair diagnostic systems is often constrained by the scarcity of labeled data. To address this challenge, our work explores the feasibility of unsupe…
Understanding the Transferability of Representations via Task-Relatedness
Akshay Mehra, Yunbei Zhang, Jihun Hamm
The growing popularity of transfer learning, due to the availability of models pre-trained on vast amounts of data, makes it imperative to understand when the knowledge of these pr…
FBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium Segmentation
Yunsung Chung, Chanho Lim, Chao Huang +2
Medical image segmentation of gadolinium enhancement magnetic resonance imaging (GE MRI) is an important task in clinical applications. However, manual annotation is time-consuming…
Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future
Byunggill Joe, Insik Shin, Jihun Hamm
Recurrent models are frequently being used in online tasks such as autonomous driving, and a comprehensive study of their vulnerability is called for. Existing research is limited…
On Certifying and Improving Generalization to Unseen Domains
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen +1
Domain Generalization (DG) aims to learn models whose performance remains high on unseen domains encountered at test-time by using data from multiple related source domains. Many e…
Efficient and Local Parallel Random Walks
Michael Kapralov, Silvio Lattanzi, Navid Nouri +1
Random walks are a fundamental primitive used in many machine learning algorithms with several applications in clustering and semi-supervised learning. Despite their relevance, the…
Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen +1
Unsupervised domain adaptation (UDA) enables cross-domain learning without target domain labels by transferring knowledge from a labeled source domain whose distribution differs fr…
Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks
Byunggill Joe, Akshay Mehra, Insik Shin +1
Electronic Health Records (EHRs) provide a wealth of information for machine learning algorithms to predict the patient outcome from the data including diagnostic information, vita…
Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
Byunggill Joe, Jihun Hamm, Sung Ju Hwang +2
Although deep neural networks have shown promising performances on various tasks, they are susceptible to incorrect predictions induced by imperceptibly small perturbations in inpu…
How Robust are Randomized Smoothing based Defenses to Data Poisoning?
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen +1
Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a…
Penalty Method for Inversion-Free Deep Bilevel Optimization
Akshay Mehra, Jihun Hamm
Solving a bilevel optimization problem is at the core of several machine learning problems such as hyperparameter tuning, data denoising, meta- and few-shot learning, and training-…
K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning
Jihun Hamm, Yung-Kyun Noh
Minimax optimization plays a key role in adversarial training of machine learning algorithms, such as learning generative models, domain adaptation, privacy preservation, and robus…
Fast Interactive Image Retrieval using large-scale unlabeled data
Akshay Mehra, Jihun Hamm, Mikhail Belkin
An interactive image retrieval system learns which images in the database belong to a user's query concept, by analyzing the example images and feedback provided by the user. The c…
Machine vs Machine: Minimax-Optimal Defense Against Adversarial Examples
Jihun Hamm, Akshay Mehra
Recently, researchers have discovered that the state-of-the-art object classifiers can be fooled easily by small perturbations in the input unnoticeable to human eyes. It is also k…
Minimax Filter: Learning to Preserve Privacy from Inference Attacks
Jihun Hamm
Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for disc…
Learning Privately from Multiparty Data
Jihun Hamm, Paul Cao, Mikhail Belkin
Learning a classifier from private data collected by multiple parties is an important problem that has many potential applications. How can we build an accurate and differentially…
Probabilistic Zero-shot Classification with Semantic Rankings
Jihun Hamm, Mikhail Belkin
In this paper we propose a non-metric ranking-based representation of semantic similarity that allows natural aggregation of semantic information from multiple heterogeneous source…
Crowd-ML: A Privacy-Preserving Learning Framework for a Crowd of Smart Devices
Jihun Hamm, Adam Champion, Guoxing Chen +2
Smart devices with built-in sensors, computational capabilities, and network connectivity have become increasingly pervasive. The crowds of smart devices offer opportunities to col…