Robin Chan
YOU?
Author Swipe
View article: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models
TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models Open
This paper introduces Virtual Try-Off (VTOFF), a novel task generating standardized garment images from single photos of clothed individuals. Unlike Virtual Try-On (VTON), which digitally dresses models, VTOFF extracts canonical garment im…
View article: New advances in universal approximation with neural networks of minimal width
New advances in universal approximation with neural networks of minimal width Open
We prove several universal approximation results at minimal or near-minimal width for approximation of $L^p(\mathbb{R}^{d_x}, \mathbb{R}^{d_y})$ and $C^0(\mathbb{R}^{d_x}, \mathbb{R}^{d_y})$ on compact sets. Our approach uses a unified cod…
View article: Machine learning identifies a 5-serum cytokine panel for the early detection of chronic atrophy gastritis patients
Machine learning identifies a 5-serum cytokine panel for the early detection of chronic atrophy gastritis patients Open
BACKGROUND: Chronic atrophy gastritis (CAG) is a high-risk pre-cancerous lesion for gastric cancer (GC). The early and accurate detection and discrimination of CAG from benign forms of gastritis (e.g. chronic superficial gastritis, CSG) is…
View article: Wuppertal Obstacle Sequences
Wuppertal Obstacle Sequences Open
images of the Wuppertal Obstacle Sequences dataset
View article: What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages
What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages Open
What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formalize it as a matter of learnability of classes of distributio…
View article: FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation
FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation Open
In the realm of fashion object detection and segmentation for online shopping images, existing state-of-the-art fashion parsing models encounter limitations, particularly when exposed to non-model-worn apparel and close-up shots. To addres…
View article: Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes
Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes Open
In the life cycle of highly automated systems operating in an open and dynamic environment, the ability to adjust to emerging challenges is crucial. For systems integrating data-driven AI-based components, rapid responses to deployment iss…
View article: <scp>GV</scp>‐971 attenuates <scp>α‐Synuclein</scp> aggregation and related pathology
<span>GV</span>‐971 attenuates <span>α‐Synuclein</span> aggregation and related pathology Open
Rationale Synucleinopathies, including Parkinson's disease (PD), multiple system atrophy (MSA), and dementia with Lewy bodies (DLB), share a distinct pathological feature, that is, a widespread accumulation of α‐synuclein (α‐syn) in the br…
View article: Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals
Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals Open
We present a human-in-the-loop dashboard tailored to diagnosing potential spurious features that NLI models rely on for predictions. The dashboard enables users to generate diverse and challenging examples by drawing inspiration from GPT-3…
View article: Lysosomal phospholipase A2 contributes to the biosynthesis of the atypical late endosome lipid bis(monoacylglycero)phosphate
Lysosomal phospholipase A2 contributes to the biosynthesis of the atypical late endosome lipid bis(monoacylglycero)phosphate Open
The late endosome/lysosome (LE/Lys) lipid bis(monoacylglycero)phosphate (BMP) plays major roles in cargo sorting and degradation, regulation of cholesterol and intercellular communication and has been linked to viral infection and neurodeg…
View article: LU-Net: Invertible Neural Networks Based on Matrix Factorization
LU-Net: Invertible Neural Networks Based on Matrix Factorization Open
LU-Net is a simple and fast architecture for invertible neural networks (INN) that is based on the factorization of quadratic weight matrices $\mathsf{A=LU}$, where $\mathsf{L}$ is a lower triangular matrix with ones on the diagonal and $\…
View article: Utilizing machine learning and lipidomics to distinguish primary lateral sclerosis from amyotrophic lateral sclerosis
Utilizing machine learning and lipidomics to distinguish primary lateral sclerosis from amyotrophic lateral sclerosis Open
Introduction/Aims There are currently no imaging or blood diagnostic biomarkers that can differentiate amyotrophic lateral sclerosis (ALS) from primary lateral sclerosis (PLS) patients early in their disease courses. Our objective is to ex…
View article: What should AI see? Using the public’s opinion to determine the perception of an AI
What should AI see? Using the public’s opinion to determine the perception of an AI Open
Deep neural networks (DNN) have made impressive progress in the interpretation of image data so that it is conceivable and to some degree realistic to use them in safety critical applications like automated driving. From an ethical standpo…
View article: Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals
Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals Open
We present a human-in-the-loop dashboard tailored to diagnosing potential spurious features that NLI models rely on for predictions. The dashboard enables users to generate diverse and challenging examples by drawing inspiration from GPT-3…
View article: Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects
Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects Open
In this work we present two video test data sets for the novel computer vision (CV) task of out of distribution tracking (OOD tracking). Here, OOD objects are understood as objects with a semantic class outside the semantic space of an und…
View article: Wuppertal Obstacle Sequences
Wuppertal Obstacle Sequences Open
images of the Wuppertal Obstacle Sequences dataset
View article: Street Obstacle Sequences
Street Obstacle Sequences Open
images and labels of the Street Obstacle Sequences dataset
View article: CARLA Wildlife Sequences
CARLA Wildlife Sequences Open
images and labels of the CARLA Wildlife Sequences dataset
View article: CARLA Wildlife Sequences
CARLA Wildlife Sequences Open
images and labels of the CARLA Wildlife Sequences dataset
View article: Street Obstacle Sequences
Street Obstacle Sequences Open
images and labels of the Street Obstacle Sequences dataset
View article: What should AI see? Using the Public's Opinion to Determine the Perception of an AI
What should AI see? Using the Public's Opinion to Determine the Perception of an AI Open
Deep neural networks (DNN) have made impressive progress in the interpretation of image data, so that it is conceivable and to some degree realistic to use them in safety critical applications like automated driving. From an ethical standp…
View article: Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning
Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning Open
Bringing deep neural networks (DNNs) into safety critical applications such as automated driving, medical imaging and finance, requires a thorough treatment of the model's uncertainties. Training deep neural networks is already resource de…
View article: Detecting and Learning the Unknown in Semantic Segmentation
Detecting and Learning the Unknown in Semantic Segmentation Open
Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task and they are usually trained on a closed set of object classes appearing in a closed operational …
View article: Detecting and Learning the Unknown in Semantic Segmentation
Detecting and Learning the Unknown in Semantic Segmentation Open
Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task, and they are usually trained on a closed set of object classes appearing in a closed operational…