paper-with-me

홈 › Papers

Unique Class Group Based Multi-Label Balancing Optimizer for Action Unit Detection

2020-03-05 · Ines Rieger, Jaspar Pahl, Dominik Seuss

Balancing methods for single-label data cannot be applied to multi-label problems as they would also resample the samples with high occurrences. We propose to reformulate this problem as an optimization problem in order to balance multi-label data. We apply this balancing algorithm to training datasets for detecting isolated facial movements, so-called Action Units. Several Action Units can describe combined emotions or physical states such as pain. As datasets in this area are limited and mostly imbalanced, we show how optimized balancing and then augmentation can improve Action Unit detection. At the IEEE Conference on Face and Gesture Recognition 2020, we ranked third in the Affective Behavior Analysis in-the-wild (ABAW) challenge for the Action Unit detection task.

📄 PDF Abstract BibTeX arXiv:2003.08751

Code (0)

등록된 구현이 없습니다.

Tasks

Action Unit DetectionGesture Recognition

Similar Papers 제목 키워드 기반

Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning

2025-01-01 · CVPR 2025 1 · Lei-Lei Ma, Shuo Xu, Ming-Kun Xie, Lei Wang 외

Modeling label correlations has always played a pivotal role in multi-label image classification (MLC), attracting significant attention from researchers. However, recent studies have overemphasized co-occurrence rel…

image-classificationImage ClassificationMixture-of-ExpertsMulti-Label Image Classification+1

Fairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification

2025-10-11 · Haohua Dong, Ana Manzano Rodríguez, Camille Guinaudeau, Shin'ichi Satoh arxiv

Face gender classification models often reflect and amplify demographic biases present in their training data, leading to uneven performance across gender and racial subgroups. We introduce pseudo-balancing, a simple and…

Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial

2021-07-13 · NeurIPS 2021 12 · Yang Liu, Jialu Wang

In this paper, we answer the question of when inserting label noise (less informative labels) can instead return us more accurate and fair models. We are primarily inspired by three observations: 1) In contrast to reduci…

FairnessInformativenessLearning with noisy labels

Multi-Granularity Regularized Re-Balancing for Class Incremental Learning

2022-06-30 · Huitong Chen, Yu Wang, QinGhua Hu

Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typi…

class-incremental learningClass Incremental LearningFault DiagnosisIncremental Learning

Sparse-Group Boosting with Balanced Selection Frequencies: A Simulation-Based Approach and R Implementation

2024-05-31 · Fabian Obster, Christian Heumann

This paper introduces a novel framework for reducing variable selection bias by balancing selection frequencies of base-learners in boosting and introduces the sgboost package in R, which implements this framework combin…

Selection biasVariable Selection