47 citations · 158 across the 12 of their papers we have counts for
13 papers
Domain-Scalable Unpaired Image Translation via Latent Space Anchoring
Siyu Huang, Jie An, Donglai Wei +3
Unpaired image-to-image translation (UNIT) aims to map images between two visual domains without paired training data. However, given a UNIT model trained on certain domains, it is…
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion
Zixiang Zhao, Haowen Bai, Jiangshe Zhang +5
Multi-modality (MM) image fusion aims to render fused images that maintain the merits of different modalities, e.g., functional highlight and detailed textures. To tackle the chall…
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
Yuanhao Cai, Jing Lin, Zudi Lin +5
Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image…
Instance Segmentation of Unlabeled Modalities via Cyclic Segmentation GAN
Leander Lauenburg, Zudi Lin, Ruihan Zhang +6
Instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segme…
Revisiting RCAN: Improved Training for Image Super-Resolution
Zudi Lin, Prateek Garg, Atmadeep Banerjee +6
Image super-resolution (SR) is a fast-moving field with novel architectures attracting the spotlight. However, most SR models were optimized with dated training strategies. In this…
Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation
Anirudh S Chakravarthy, Won-Dong Jang, Zudi Lin +3
Video instance segmentation aims to detect, segment, and track objects in a video. Current approaches extend image-level segmentation algorithms to the temporal domain. However, th…
PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics
Zudi Lin, Donglai Wei, Jeff Lichtman +1
We present PyTorch Connectomics (PyTC), an open-source deep-learning framework for the semantic and instance segmentation of volumetric microscopy images, built upon PyTorch. We de…
Asymmetric 3D Context Fusion for Universal Lesion Detection
Jiancheng Yang, Yi He, Kaiming Kuang +3
Modeling 3D context is essential for high-performance 3D medical image analysis. Although 2D networks benefit from large-scale 2D supervised pretraining, it is weak in capturing 3D…
AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions
Donglai Wei, Kisuk Lee, Hanyu Li +13
Electron microscopy (EM) enables the reconstruction of neural circuits at the level of individual synapses, which has been transformative for scientific discoveries. However, due t…
NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter Scale
Zudi Lin, Donglai Wei, Mariela D. Petkova +12
Segmenting 3D cell nuclei from microscopy image volumes is critical for biological and clinical analysis, enabling the study of cellular expression patterns and cell lineages. Howe…
White-Box Adversarial Defense via Self-Supervised Data Estimation
Zudi Lin, Hanspeter Pfister, Ziming Zhang
In this paper, we study the problem of how to defend classifiers against adversarial attacks that fool the classifiers using subtly modified input data. In contrast to previous wor…
A Topological Nomenclature for 3D Shape Analysis in Connectomics
Abhimanyu Talwar, Zudi Lin, Donglai Wei +7
One of the essential tasks in connectomics is the morphology analysis of neurons and organelles like mitochondria to shed light on their biological properties. However, these biolo…
FDive: Learning Relevance Models using Pattern-based Similarity Measures
Frederik L. Dennig, Tom Polk, Zudi Lin +3
The detection of interesting patterns in large high-dimensional datasets is difficult because of their dimensionality and pattern complexity. Therefore, analysts require automated…