18 citations · 45 across the 16 of their papers we have counts for
16 papers
Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao +3
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.).…
CLR: Channel-wise Lightweight Reprogramming for Continual Learning
Yunhao Ge, Yuecheng Li, Shuo Ni +3
Continual learning aims to emulate the human ability to continually accumulate knowledge over sequential tasks. The main challenge is to maintain performance on previously learned…
Robustness Analysis on Foundational Segmentation Models
Madeline Chantry Schiappa, Shehreen Azad, Sachidanand VS +4
Due to the increase in computational resources and accessibility of data, an increase in large, deep learning models trained on copious amounts of multi-modal data using self-super…
Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models
Yunhao Ge, Jie Ren, Jiaping Zhao +4
We focus on the challenge of out-of-distribution (OOD) detection in deep learning models, a crucial aspect in ensuring reliability. Despite considerable effort, the problem remains…
Lightweight Learner for Shared Knowledge Lifelong Learning
Yunhao Ge, Yuecheng Li, Di Wu +12
In Lifelong Learning (LL), agents continually learn as they encounter new conditions and tasks. Most current LL is limited to a single agent that learns tasks sequentially. Dedicat…
EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao +2
We propose EM-PASTE: an Expectation Maximization(EM) guided Cut-Paste compositional dataset augmentation approach for weakly-supervised instance segmentation using only image-level…
Improving Zero-shot Generalization and Robustness of Multi-modal Models
Yunhao Ge, Jie Ren, Andrew Gallagher +6
Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particu…
Neural-Sim: Learning to Generate Training Data with NeRF
Yunhao Ge, Harkirat Behl, Jiashu Xu +6
Training computer vision models usually requires collecting and labeling vast amounts of imagery under a diverse set of scene configurations and properties. This process is incredi…
Contributions of Shape, Texture, and Color in Visual Recognition
Yunhao Ge, Yao Xiao, Zhi Xu +2
We investigate the contributions of three important features of the human visual system (HVS)~ -- ~shape, texture, and color ~ -- ~to object classification. We build a humanoid vis…
Invariant Structure Learning for Better Generalization and Causal Explainability
Yunhao Ge, Sercan Ö. Arik, Jinsung Yoon +3
Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Lear…
DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao +3
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-toimage synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.).…
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization
Yunhao Ge, Zhi Xu, Yao Xiao +3
We focus on controllable disentangled representation learning (C-Dis-RL), where users can control the partition of the disentangled latent space to factorize dataset attributes (co…
Beneficial Perturbation Network for designing general adaptive artificial intelligence systems
Shixian Wen, Amanda Rios, Yunhao Ge +1
The human brain is the gold standard of adaptive learning. It not only can learn and benefit from experience, but also can adapt to new situations. In contrast, deep neural network…
Zero-shot Synthesis with Group-Supervised Learning
Yunhao Ge, Sami Abu-El-Haija, Gan Xin +1
Visual cognition of primates is superior to that of artificial neural networks in its ability to 'envision' a visual object, even a newly-introduced one, in different attributes in…
Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition
Yunhao Ge, Jiaping Zhao, Laurent Itti
Object pose increases intraclass object variance which makes object recognition from 2D images harder. To render a classifier robust to pose variations, most deep neural networks t…
Synthesis and Inpainting-Based MR-CT Registration for Image-Guided Thermal Ablation of Liver Tumors
Dongming Wei, Sahar Ahmad, Jiayu Huo +7
Thermal ablation is a minimally invasive procedure for treat-ing small or unresectable tumors. Although CT is widely used for guiding ablation procedures, the contrast of tumors ag…