44 citations · 60 across the 11 of their papers we have counts for
11 papers
Cybernaut: Towards Reliable Web Automation
Ankur Tomar, Hengyue Liang, Indranil Bhattacharya +2
The emergence of AI-driven web automation through Large Language Models (LLMs) offers unprecedented opportunities for optimizing digital workflows. However, deploying such systems…
A Baseline Method for Removing Invisible Image Watermarks using Deep Image Prior
Hengyue Liang, Taihui Li, Ju Sun
Image watermarks have been considered a promising technique to help detect AI-generated content, which can be used to protect copyright or prevent fake image abuse. In this work, w…
Selective Classification Under Distribution Shifts
Hengyue Liang, Le Peng, Ju Sun
In selective classification (SC), a classifier abstains from making predictions that are likely to be wrong to avoid excessive errors. To deploy imperfect classifiers -- either due…
Optimization and Optimizers for Adversarial Robustness
Hengyue Liang, Buyun Liang, Le Peng +3
Empirical robustness evaluation (RE) of deep learning models against adversarial perturbations entails solving nontrivial constrained optimization problems. Existing numerical algo…
Optimization for Robustness Evaluation beyond Metrics
Hengyue Liang, Buyun Liang, Ying Cui +2
Empirical evaluation of deep learning models against adversarial attacks entails solving nontrivial constrained optimization problems. Popular algorithms for solving these constrai…
Early Stopping for Deep Image Prior
Hengkang Wang, Taihui Li, Zhong Zhuang +3
Deep image prior (DIP) and its variants have showed remarkable potential for solving inverse problems in computer vision, without any extra training data. Practical DIP models are…
Self-Validation: Early Stopping for Single-Instance Deep Generative Priors
Taihui Li, Zhong Zhuang, Hengyue Liang +3
Recent works have shown the surprising effectiveness of deep generative models in solving numerous image reconstruction (IR) tasks, even without training data. We call these models…
Rethinking Transfer Learning for Medical Image Classification
Le Peng, Hengyue Liang, Gaoxiang Luo +2
Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-de…
Attribute-Based Robotic Grasping with One-Grasp Adaptation
Yang Yang, Yuanhao Liu, Hengyue Liang +2
Robotic grasping is one of the most fundamental robotic manipulation tasks and has been actively studied. However, how to quickly teach a robot to grasp a novel target object in cl…
Learning Visual Affordances with Target-Orientated Deep Q-Network to Grasp Objects by Harnessing Environmental Fixtures
Hengyue Liang, Xibai Lou, Yang Yang +1
This paper introduces a challenging object grasping task and proposes a self-supervised learning approach. The goal of the task is to grasp an object which is not feasible with a s…
A Deep Learning Approach to Grasping the Invisible
Yang Yang, Hengyue Liang, Changhyun Choi
We study an emerging problem named "grasping the invisible" in robotic manipulation, in which a robot is tasked to grasp an initially invisible target object via a sequence of push…