Joint Classification

Joint classification research focuses on simultaneously performing multiple classification tasks, leveraging shared information and improving overall performance compared to independent approaches. Current work explores diverse applications, from medical image analysis (combining segmentation and classification) to robust face recognition and fine-grained object classification, employing techniques like contrastive clustering, ensemble methods, and knowledge distillation within various neural network architectures. These advancements enhance accuracy, robustness (especially against adversarial attacks), and explainability, leading to more reliable and trustworthy results across numerous fields.

Papers

November 14, 2024

Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning
Dunwei Tu, Huiyu Yi, Tieyi Zhang, Ruotong Li, Furao Shen, Jian Zhao
Class Incremental Learning Nearest Neighbor Logit Calibration Joint Classification

December 7, 2023

Improved Face Representation via Joint Label Classification and Supervised Contrastive Clustering
Zhenduo Zhang
Face Recognition Face Verification Contrastive Clustering Angular Margin Loss Face Representation Joint Classification

July 7, 2023

Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning
Vladan Stojnić, Zakaria Laskar, Giorgos Tolias
Ensemble Learning Pseudo Labeling Deep Active Learning Semi Supervision Semi Supervised Active Learning Joint Classification

April 19, 2023

Knowledge Distillation Under Ideal Joint Classifier Assumption
Huayu Li, Xiwen Chen, Gregory Ditzler, Janet Roveda, Ao Li
Knowledge Distillation Softmax Function Joint Classification

March 17, 2023

Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation
Kai Ren, Ke Zou, Xianjie Liu, Yidi Chen, Xuedong Yuan, Xiaojing Shen, Meng Wang, Huazhu Fu
Segmentation Based Approach Medical Image Analysis Evidential Deep Learning Mutual Learning Joint Classification

October 26, 2022

Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes
Sina Baharlouei, Fatemeh Sheikholeslami, Meisam Razaviyayn, Zico Kolter
Adversarial Attack Adversarial Example Adversarial Robustness Abstention Ability Model Degeneracy Detection Class Joint Classification

September 20, 2022

Fine-grained Classification of Solder Joints with {\alpha}-skew Jensen-Shannon Divergence
Furkan Ulger, Seniha Esen Yuksel, Atila Yilmaz, Dincer Gokcen
Fine Grained Fine Grained Image Classification Entropy Regularized Jensen Shannon Divergence Jacobian Regularization Joint Classification

December 20, 2021

Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction
Dongfang Li, Baotian Hu, Qingcai Chen, Tujie Xu, Jingcong Tao, Yunan Zhang
Adversarial Attack Native Robustness High Explainability Rationale Extraction Joint Classification

Joint Classification

Papers

Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning

Improved Face Representation via Joint Label Classification and Supervised Contrastive Clustering

Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning

Knowledge Distillation Under Ideal Joint Classifier Assumption

Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation

Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes

Fine-grained Classification of Solder Joints with {\alpha}-skew Jensen-Shannon Divergence

Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction