Multi-Label Class Balancing Algorithm for Action Unit Detection
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）
Jaspar Pahl, Ines Rieger, Dominik Seuss
备注：
This submission is subject to the Action Unit detection task of the Affective Behavior Analysis in-the-wild (ABAW) challenge at the IEEE Conference on Face and Gesture Recognition 2020
Isolated facial movements, so-called Action Units, can describe combined emotions or physical states such as pain. As datasets are limited and mostly imbalanced, we present an approach incorporating a multi-label class balancing algorithm. This submission is subject to the Action Unit detection task of the Affective Behavior Analysis in-the-wild (ABAW) challenge at the IEEE Conference on Face and Gesture Recognition 2020.
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）
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 detectio…
Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise
Department of Information and Computer Sciences, University of Hawai‘i at Manoa（夏威夷大学马诺亚分校信息与计算机科学系）；Department of Computer Science, University of Pretoria（pretoria大学计算机科学系）
Centrum Wiskunde & Informatica（数学与计算机科学研究所）；Leiden University（莱顿大学）；Eindhoven University of Technology（埃因霍温理工大学）
We present three parallel-beam tomographic datasets of 94 apples with internal defects along with defect label files. The datasets are prepared for development and testing of data-driven, learning-based image reconstruction, segmentation and post-processing methods. The three versions are a noiseless simulation; simulation with added Gaussian noise, and with scattering noise. The datasets are based on real 3D X-ray CT data and their subsequent volume reconstructions. The ground truth images, based on the volume reconstructions, are also available through this project. Apples contain various de…
Fairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification
National Institute of Informatics, Japan（日本信息机构国家研究所）；INESC-ID, Instituto Superior Técnico, University of Lisbon, Portugal（里斯本大学技术高等学院、INESC-ID，葡萄牙）；University of Amsterdam, The Netherlands（荷兰阿姆斯特丹大学）；LIMSI, CNRS / Université Paris-Saclay, France（法国CNRS/巴黎萨克雷大学LIMSI）
Nanyang Technological University（南洋理工大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Chongqing University（重庆大学）
Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance. Recent studies found that directly training with out-of-distribution data (i.e., open-set samples) in a semi-supervised manner would harm the generalization performance. In this work, we theoretically show that out-of-distribution data can still be leveraged to augment the minority classes from a Bayesian perspective. Based on this motivation, we propose a novel method called Open-sampling, which utilizes open-set noisy labels to re-balance the class priors of the training dataset. For e…
Facial action units allow an objective, standardized description of facial micro movements which can be used to describe emotions in human faces. Annotating data for action units is an expensive and time-consuming task, which leads to a scarce data situation. By combining multiple datasets from different studies, the amount of training data for a machine learning algorithm can be increased in order to create robust models for automated, multi-label action unit detection. However, every study annotates different action units, leading to a tremendous amount of missing labels in a combined databa…
Graduate School of Informatics, Kyoto University（京都大学信息学研究生院）；RIKEN Center for Advanced Intelligence Project (AIP)（理化学研究所先进智能项目中心）
Employing one or more additional classifiers to break the self-learning loop in tracing-by-detection has gained considerable attention. Most of such trackers merely utilize the redundancy to address the accumulating label error in the tracking loop, and suffer from high computational complexity as well as tracking challenges that may interrupt all classifiers (e.g. temporal occlusions). We propose the active co-tracking framework, in which the main classifier of the tracker labels samples of the video sequence, and only consults auxiliary classifier when it is uncertain. Based on the source of…
Tianjin University（天津大学）；Haihe Laboratory of Information Technology Application Innovation（海河实验室信息技术应用创新实验室）
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 typical approach is to use a few exemplars to avoid forgetting old knowledge. In such a scenario, data imbalance between old and new classes is a key issue that leads to performance degradation of the model. Several strategies have been designed to rectify the bias towards the new classes due to data imbalance. However, they heavily rely on the assumptions of the bias relation betw…
Generative adversarial networks (GANs) are one of the most powerful generative models, but always require a large and balanced dataset to train. Traditional GANs are not applicable to generate minority-class images in a highly imbalanced dataset. Balancing GAN (BAGAN) is proposed to mitigate this problem, but it is unstable when images in different classes look similar, e.g. flowers and cells. In this work, we propose a supervised autoencoder with an intermediate embedding model to disperse the labeled latent vectors. With the improved autoencoder initialization, we also build an architecture …
Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning
Information Technology University of Punjab（旁遮普信息技术大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
In a typical multi-label setting, a picture contains on average few positive labels, and many negative ones. This positive-negative imbalance dominates the optimization process, and can lead to under-emphasizing gradients from positive labels during training, resulting in poor accuracy. In this paper, we introduce a novel asymmetric loss ("ASL"), which operates differently on positive and negative samples. The loss enables to dynamically down-weights and hard-thresholds easy negative samples, while also discarding possibly mislabeled samples. We demonstrate how ASL can balance the probabilitie…
Label distributions in camera-trap images are highly imbalanced and long-tailed, resulting in neural networks tending to be biased towards head-classes that appear frequently. Although long-tail learning has been extremely explored to address data imbalances, few studies have been conducted to consider camera-trap characteristics, such as multi-domain and multi-frame setup. Here, we propose a unified framework and introduce two datasets for long-tailed camera-trap recognition. We first design domain experts, where each expert learns to balance imperfect decision boundaries caused by data imbal…
Improving Multi-Label Contrastive Learning by Leveraging Label Distribution
College of Computer Science and Software Engineering, Hohai University（河海大学计算机与软件学院）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
University of Electronic Science and Technology of China（中国电子科技大学）
Facial Action Coding System is an important approach of facial expression analysis.This paper describes our submission to the third Affective Behavior Analysis (ABAW) 2022 competition. We proposed a transfomer based model to detect facial action unit (FAU) in video. To be specific, we firstly trained a multi-modal model to extract both audio and visual feature. After that, we proposed a action units correlation module to learn relationships between each action unit labels and refine action unit detection result. Experimental results on validation dataset shows that our method achieves better p…
Improving 3D Occupancy Prediction through Class-balancing Loss and Multi-scale Representation
National University of Singapore (NUS)（新加坡国立大学）；Desay SV Automotive Singapore Pte. Ltd.（德赛西威汽车新加坡私人有限公司）；Singapore University of Technology and Design (SUTD)（新加坡科技设计大学）；Nanyang Technological University (NTU)（南洋理工大学）
Action Unit (AU) Detection is the branch of affective computing that aims at recognizing unitary facial muscular movements. It is key to unlock unbiased computational face representations and has therefore aroused great interest in the past few years. One of the main obstacles toward building efficient deep learning based AU detection system is the lack of wide facial image databases annotated by AU experts. In that extent the ABAW challenge paves the way toward better AU detection as it involves a 2M frames AU annotated dataset. In this paper, we present our submission to the ABAW3 challenge.…
South China University of Technology（华南理工大学）；University of Oulu（奥卢大学）；Haaga-Helia University of Applied Sciences（哈格-赫利尔应用科学大学）
High-quality annotated images are significant to deep facial expression recognition (FER) methods. However, uncertain labels, mostly existing in large-scale public datasets, often mislead the training process. In this paper, we achieve uncertain label correction of facial expressions using auxiliary action unit (AU) graphs, called ULC-AG. Specifically, a weighted regularization module is introduced to highlight valid samples and suppress category imbalance in every batch. Based on the latent dependency between emotions and AUs, an auxiliary branch using graph convolutional layers is added to e…
University of Science and Technology of China（中国科学技术大学）
Current works formulate facial action unit (AU) recognition as a supervised learning problem, requiring fully AU-labeled facial images during training. It is challenging if not impossible to provide AU annotations for large numbers of facial images. Fortunately, AUs appear on all facial images, whether manually labeled or not, satisfy the underlying anatomic mechanisms and human behavioral habits. In this paper, we propose a deep semi-supervised framework for facial action unit recognition from partially AU-labeled facial images. Specifically, the proposed deep semi-supervised AU recognition a…
State University of New York at Binghamton（纽约州立大学宾汉姆顿分校）
Recent studies on the automatic detection of facial action unit (AU) have extensively relied on large-sized annotations. However, manually AU labeling is difficult, time-consuming, and costly. Most existing semi-supervised works ignore the informative cues from the temporal domain, and are highly dependent on densely annotated videos, making the learning process less efficient. To alleviate these problems, we propose a deep semi-supervised framework Knowledge-Spreader (KS), which differs from conventional methods in two aspects. First, rather than only encoding human knowledge as constraints, …
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Facial action units (AUs) recognition is essential for emotion analysis and has been widely applied in mental state analysis. Existing work on AU recognition usually requires big face dataset with AU labels; however, manual AU annotation requires expertise and can be time-consuming. In this work, we propose a semi-supervised approach for AU recognition utilizing a large number of web face images without AU labels and a relatively small face dataset with AU annotations inspired by the co-training methods. Unlike traditional co-training methods that require provided multi-view features and model…
