Classification Network

Classification networks are artificial neural networks designed to categorize input data, such as images or text, into predefined classes. Current research emphasizes improving accuracy, interpretability, and efficiency, exploring architectures like convolutional neural networks (CNNs), transformers, and hybrid models that combine both. These advancements are crucial for various applications, including medical image analysis, object recognition, and natural language processing, driving progress in fields ranging from healthcare to computer vision.

Papers

April 9, 2022

Knowledge-Free Black-Box Watermark and Ownership Proof for Image Classification Neural Networks
Fangqi Li, Shilin Wang
Watermarking Method Agnostic Watermarking Classification Network Ownership Verification Watermarking Scheme Black Box Watermarking

February 25, 2022

ciscNet -- A Single-Branch Cell Instance Segmentation and Classification Network
Moritz Böhland, Oliver Neumann, Marcel P. Schilling, Markus Reischl, Ralf Mikut, Katharina Löffler, Tim Scherr
Instance Segmentation Nucleus Segmentation Classification Network Colon Nucleus Identification Conic Constraint

December 30, 2021

On the Role of Neural Collapse in Transfer Learning
Tomer Galanti, András György, Marcus Hutter
Transfer Learning Integral Role Meaningful Representation Neural Collapse Classification Network

November 29, 2021

Adversarial Training for a Hybrid Approach to Aspect-Based Sentiment Analysis
Ron Hochstenbach, Flavius Frasincar, Maria Mihaela Trusca
Adversarial Training Sentiment Analysis Adversarial Learning User Sentiment Aspect Based Sentiment Analysis Hybrid Approach Classification Network

Classification Network

Papers

Knowledge-Free Black-Box Watermark and Ownership Proof for Image Classification Neural Networks

ciscNet -- A Single-Branch Cell Instance Segmentation and Classification Network

On the Role of Neural Collapse in Transfer Learning

Adversarial Training for a Hybrid Approach to Aspect-Based Sentiment Analysis