True Class

"True class" research broadly focuses on improving the accuracy and efficiency of classification tasks across diverse data types and learning paradigms. Current efforts concentrate on developing novel algorithms and model architectures, such as graph neural networks and physics-informed neural networks, to address challenges like class imbalance, catastrophic forgetting in incremental learning, and the limitations of traditional activation functions. This research is significant for advancing machine learning capabilities in various fields, including medical image analysis, natural language processing, and robotics, by enabling more robust and reliable classification models.

Papers

May 4, 2023

On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
Yicheng Li, Zixiong Yu, Guhan Chen, Qian Lin
Neural Tangent Kernel Open Domain True Class Wide Neural Network Kernel Function Eigenvalue Decay

May 3, 2023

Class adaptive threshold and negative class guided noisy annotation robust Facial Expression Recognition
Darshan Gera, Badveeti Naveen Siva Kumar, Bobbili Veerendra Raj Kumar, S Balasubramanian
Label Noise Facial Expression Recognition Expression Recognition True Class Noisy Annotation Adaptive Threshold

May 2, 2023

Class based Influence Functions for Error Detection
Thang Nguyen-Duc, Hoang Thanh-Tung, Quan Hung Tran, Dang Huu-Tien, Hieu Ngoc Nguyen, Anh T. V. Dau, Nghi D. Q. Bui
Deep Network Core Stability True Class Error Detection Influence Function Large Scale Datasets

April 11, 2023

Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per class
Maximilian Nielsen, Laura Wenderoth, Thilo Sentker, René Werner
Self Supervised State of the Art Medical Image Analysis Self Supervision Medical Image Classification Image Representation True Class Training Sample

April 6, 2023

A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation
Azal Ahmad Khan, Omkar Chaudhari, Rohitash Chandra
Data Augmentation Global Evaluation Ensemble Learning Class Imbalance True Class New Combination Imbalanced Datasets

March 21, 2023

Analytical Conjugate Priors for Subclasses of Generalized Pareto Distributions
Masataro Asai
Pareto Optimal True Class Extreme Value Theory Gaussian Prior Tail Risk Parameter Distribution

March 8, 2023

Class Cardinality Comparison as a Fermi Problem
Shrestha Ghosh, Simon Razniewski, Gerhard Weikum
True Class Cardinality Estimation Group Cardinality Fermi LAT

February 3, 2023

Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation
Pengcheng Xu, Boyu Wang, Charles Ling
Feature Alignment True Class Domain Variation Target Domain Adaptation

December 30, 2022

PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models
Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky
Recurrent Neural Network State Space Model True Class Stochastic Dynamical System Probably Approximately Correct PAC Bayes Bound

December 19, 2022

Human in the loop: How to effectively create coherent topics by manually labeling only a few documents per class
Anton Thielmann, Christoph Weisser, Benjamin Säfken
Shot Learning Human Generated Topic Modeling True Class Document Relevance Topic Detection Shot Approach

December 11, 2022

FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification
Tingyu Xia, Yue Wang, Yuan Tian, Yi Chang
Text Classification Weakly Supervised Learning True Class Efficient Approach Weakly Supervised Text Classification Dense Text

November 24, 2022

Zeroth-Order Alternating Gradient Descent Ascent Algorithms for a Class of Nonconvex-Nonconcave Minimax Problems
Zi Xu, Zi-Qi Wang, Jun-Lin Wang, Yu-Hong Dai
True Class Zeroth Order Gradient Descent Ascent Minimax Problem Lloyd Algorithm

November 23, 2022

November 22, 2022

Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation
Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov, Joost van de Weijer
Vision Transformer True Class Exemplar Image ViT Model Free Continual Learning Feature Drift Exemplar Free Method Exemplar Free

October 31, 2022

Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
Simone Rossetti, Damiano Zappia, Marta Sanzari, Marco Schaerf, Fiora Pirri
Vision Transformer Semantic Segmentation Self Supervised Learning Segmentation Mask Object Shape Weakly Supervised Semantic Segmentation True Class Class Representation Max Pooling

October 27, 2022

Class Based Thresholding in Early Exit Semantic Segmentation Networks
Alperen Görmez, Erdem Koyuncu
Semantic Segmentation Model Neural Collapse True Class Automatic Thresholding Early Exit Early Exit Neural Network Masking Rate

September 16, 2022

Continual Learning for Class- and Domain-Incremental Semantic Segmentation
Tobias Kalb, Masoud Roschani, Miriam Ruf, Jürgen Beyerer
Continual LEArning Continual Learning True Class Continual Semantic Segmentation Incremental Semantic Segmentation Continual Object Detection Class Incremental Semantic

August 6, 2022

Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
Jiaxin Qi, Kaihua Tang, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang
Context Information Distribution Generalization True Class Alpha Invariance Contextual Biasing Biased Classifier Context Bias

July 28, 2022

Expanding the class of global objective functions for dissimilarity-based hierarchical clustering
Sebastien Roch
Objective Function True Class Clustering Method Greedy Algorithm Phylogenetic Tree

True Class

Papers

On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains

Class adaptive threshold and negative class guided noisy annotation robust Facial Expression Recognition

Class based Influence Functions for Error Detection

Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per class

A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation

Analytical Conjugate Priors for Subclasses of Generalized Pareto Distributions

Class Cardinality Comparison as a Fermi Problem

Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation

PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models

Human in the loop: How to effectively create coherent topics by manually labeling only a few documents per class

FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification

Zeroth-Order Alternating Gradient Descent Ascent Algorithms for a Class of Nonconvex-Nonconcave Minimax Problems

Reconnoitering the class distinguishing abilities of the features, to know them better

One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learning

Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation

Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation

Class Based Thresholding in Early Exit Semantic Segmentation Networks

Continual Learning for Class- and Domain-Incremental Semantic Segmentation

Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization

Expanding the class of global objective functions for dissimilarity-based hierarchical clustering