Classification on long-tailed distributed data is a challenging problem, which suffers from serious class-imbalance and accordingly unpromising performance especially on tail classes. Recently, the ensembling based methods achieve the state-of-the-art performance and show great potential. However, there are two limitations for current methods. First, their predictions are not trustworthy for failure-sensitive applications. This is especially harmful for the tail classes where the wrong predictions is basically frequent. Second, they assign unified numbers of experts to all samples, which is redundant for easy samples with excessive computational cost. To address these issues, we propose a Trustworthy Long-tailed Classification (TLC) method to jointly conduct classification and uncertainty estimation to identify hard samples in a multi-expert framework. Our TLC obtains the evidence-based uncertainty (EvU) and evidence for each expert, and then combines these uncertainties and evidences under the Dempster-Shafer Evidence Theory (DST). Moreover, we propose a dynamic expert engagement to reduce the number of engaged experts for easy samples and achieve efficiency while maintaining promising performances. Finally, we conduct comprehensive experiments on the tasks of classification, tail detection, OOD detection and failure prediction. The experimental results show that the proposed TLC outperforms existing methods and is trustworthy with reliable uncertainty.
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Amazon Web Services（亚马逊云科技）
Existing out-of-distribution (OOD) detection methods are typically benchmarked on training sets with balanced class distributions. However, in real-world applications, it is common for the training sets to have long-tailed distributions. In this work, we first demonstrate that existing OOD detection methods commonly suffer from significant performance degradation when the training set is long-tail distributed. Through analysis, we posit that this is because the models struggle to distinguish the minority tail-class in-distribution samples, from the true OOD samples, making the tail classes mor…
Recent years have witnessed a rapid development of automated methods for skin lesion diagnosis and classification. Due to an increasing deployment of such systems in clinics, it has become important to develop a more robust system towards various Out-of-Distribution(OOD) samples (unknown skin lesions and conditions). However, the current deep learning models trained for skin lesion classification tend to classify these OOD samples incorrectly into one of their learned skin lesion categories. To address this issue, we propose a simple yet strategic approach that improves the OOD detection perfo…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of tail over head, as the test distribution is assumed to be balanced; however, when the test is as imbalanced as the long-tailed training data -- let the test respect Zipf's law of nature -- the tail bias is no longer beneficial overall because it hurts the head majorities. In this paper, we propose Cross-Domain Empirical Risk Minimization (xERM) for training an unbiased model to achieve strong performances on both test dis…
Huazhong University of Science and Technology（华中科技大学）
The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model. In this work, we propose a new method, Gradual Balanced Loss and Adaptive Feature Generator (GLAG) to alleviate imbalance. GLAG first learns a balanced and robust feature model with Gradual Balanced Loss, then fixes the feature model and augments the under-represented tail classes on the feature level with the knowledge from well-represented head classes. And the generated samples are mixed up with real training samples during training epochs. Gradual Balanced Loss is a general loss and …
With the maturing of deep learning systems, trustworthiness is becoming increasingly important for model assessment. We understand trustworthiness as the combination of explainability and robustness. Generative classifiers (GCs) are a promising class of models that are said to naturally accomplish these qualities. However, this has mostly been demonstrated on simple datasets such as MNIST and CIFAR in the past. In this work, we firstly develop an architecture and training scheme that allows GCs to operate on a more relevant level of complexity for practical computer vision, namely the ImageNet…
Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）
We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. Compared to conventional single-label classification problem, multi-label recognition problems are often more challenging due to two significant issues, namely the co-occurrence of labels and the dominance of negative labels (when treated as multiple binary classification problems). The Distribution-Balanced Loss tackles these issues through two key modifications to the standard binary cross-entropy loss: 1) a new way to re-balance the weights …
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Noah’s Ark Lab, Shenzhen, Huawei Technologies Co. Ltd（华为技术有限公司诺亚方舟实验室）
Real-world data usually present long-tailed distributions. Training on imbalanced data tends to render neural networks perform well on head classes while much worse on tail classes. The severe sparseness of training instances for the tail classes is the main challenge, which results in biased distribution estimation during training. Plenty of efforts have been devoted to ameliorating the challenge, including data re-sampling and synthesizing new training instances for tail classes. However, no prior research has exploited the transferable knowledge from head classes to tail classes for calibra…
Long-tailed classification poses a challenge due to its heavy imbalance in class probabilities and tail-sensitivity risks with asymmetric misprediction costs. Recent attempts have used re-balancing loss and ensemble methods, but they are largely heuristic and depend heavily on empirical results, lacking theoretical explanation. Furthermore, existing methods overlook the decision loss, which characterizes different costs associated with tailed classes. This paper presents a general and principled framework from a Bayesian-decision-theory perspective, which unifies existing techniques including …
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Aberystwyth University（阿伯里斯特威斯大学）
In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME). Our method is inspired by the observation that networks trained on less imbalanced subsets of the distribution often yield better performances than their jointly-trained counterparts. We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. Spec…
Training on datasets with long-tailed distributions has been challenging for major recognition tasks such as classification and detection. To deal with this challenge, image resampling is typically introduced as a simple but effective approach. However, we observe that long-tailed detection differs from classification since multiple classes may be present in one image. As a result, image resampling alone is not enough to yield a sufficiently balanced distribution at the object level. We address object-level resampling by introducing an object-centric memory replay strategy based on dynamic, ep…
LPT++: Efficient Training on Mixture of Long-tailed Experts
School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）；The Hong Kong Polytechnic University（香港理工大学）
Beijing Institute of Technology（北京理工大学）；Meituan（美团）
Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge. This motivates us to check the hypothesis that prompt-tuning is also a promising choice for long-tailed classification, since the tail classes are intuitively few-shot ones. To achieve this aim, we conduct empirical studies to examine the hypothesis. The results demonstrate that prompt-tuning makes pretrained language models at least good long-tailed learners. For intuitions on why prompt-tuning can achieve good performance in long-tailed classif…
The Chinese University of Hong Kong（香港中文大学）；UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）
Real world data often have a long-tailed and open-ended distribution. A practical recognition system must classify among majority and minority classes, generalize from a few known instances, and acknowledge novelty upon a never seen instance. We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes. OLTR must handle imbalanced classification, few-shot learning, and open-set recognition in one integrated algorithm, whereas existing classification a…
An Enhanced Classification Method Based on Adaptive Multi-Scale Fusion for Long-tailed Multispectral Point Clouds
School of Electronics and Information Engineering（电子信息工程学院）；Harbin Institute of Technology（哈尔滨工业大学）；the Department of Telecommunications and Information Processing（电信与信息处理系）
Nanyang Technological University（南洋理工大学）；University of California, Berkeley（加州大学伯克利分校）；International Computer Science Institute（国际计算机科学研究所）；The Chinese University of Hong Kong（香港中文大学）；Google Inc.（谷歌公司）
Real world data often exhibits a long-tailed and open-ended (with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and acknowledge novelty upon the instances of unseen classes (open classes). We define Open Long-Tailed Recognition++ (OLTR++) as learning from such naturally distributed data and optimizing for the classification accuracy over a balanced test set which includes both known and open classes. OLTR++ handles imbalanced classification, few-shot learning, open-set recogniti…
We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions. Unlike conventional long-tail classifiers which operate on converged - and possibly overfit - models, we demonstrate that an approach based on gradient dot product agreement can isolate long-tailed data early on during model training and improve performance by dynamically picking higher sample weights for that data. We show that such upweighting leads to model improvements for both classification and regression models, the latter of which are rel…
SenseTime Research（商汤科技研究院）；Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong（香港中文大学）
Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distributions. In this paper, we show that the Softmax function, though used in most classification tasks, gives a biased gradient estimation under the long-tailed setup. This paper presents Balanced Softmax, an elegant unbiased extension of Softmax, to accommodate the label distribution shift between training and testing. Theoretically, we derive the generalization bound for multiclass Softmax regression and show our loss m…
Extracting Clean and Balanced Subset for Noisy Long-tailed Classification
Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；CSIRO’s Data61（联邦科学与工业研究组织数据61部门）；The University of Sydney（悉尼大学）；School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）
The natural world often follows a long-tailed data distribution where only a few classes account for most of the examples. This long-tail causes classifiers to overfit to the majority class. To mitigate this, prior solutions commonly adopt class rebalancing strategies such as data resampling and loss reshaping. However, by treating each example within a class equally, these methods fail to account for the important notion of example hardness, i.e., within each class some examples are easier to classify than others. To incorporate this notion of hardness into the learning process, we propose th…
Extreme Multi-label Text Classification (XMTC) has been a tough challenge in machine learning research and applications due to the sheer sizes of the label spaces and the severe data scarce problem associated with the long tail of rare labels in highly skewed distributions. This paper addresses the challenge of tail label prediction by proposing a novel approach, which combines the effectiveness of a trained bag-of-words (BoW) classifier in generating informative label descriptions under severe data scarce conditions, and the power of neural embedding based retrieval models in mapping input do…
Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the gradients flow. Even though CNNs can correctly classify images, the underlying saliency maps could be erroneous in many cases. This can result in skepticism as to the validity of the model or its interpretation. We propose a novel approach for training trustworthy CNNs by penalizing parameter choices that result in inaccurate saliency maps generated during tra…
St. Pölten Univ. of Applied Sciences（圣珀尔滕应用科学大学）；Orthopaedic Hospital Vienna-Speising（维也纳-施派辛骨科医院）
Three-dimensional clinical gait analysis is essential for selecting optimal treatment interventions for patients with cerebral palsy (CP), but generates a large amount of time series data. For the automated analysis of these data, machine learning approaches yield promising results. However, due to their black-box nature, such approaches are often mistrusted by clinicians. We propose gaitXplorer, a visual analytics approach for the classification of CP-related gait patterns that integrates Grad-CAM, a well-established explainable artificial intelligence algorithm, for explanations of machine l…
Shanghai Jiao Tong University（上海交通大学）；Hong Kong University of Science and Technology（香港科技大学）；Qing Yuan Research Institute（清源研究院）；Shanghai Qi Zhi Institute（上海期智研究院）
Long-tailed image recognition presents massive challenges to deep learning systems since the imbalance between majority (head) classes and minority (tail) classes severely skews the data-driven deep neural networks. Previous methods tackle with data imbalance from the viewpoints of data distribution, feature space, and model design, etc. In this work, instead of directly learning a recognition model, we suggest confronting the bottleneck of head-to-tail bias before classifier learning, from the previously omitted perspective of balancing label space. To alleviate the head-to-tail bias, we prop…
CXR-LT 2024: A MICCAI challenge on long-tailed, multi-label, and zero-shot disease classification from chest X-ray
University of Minnesota（明尼苏达大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Weill Cornell Medicine（威尔康奈尔医学院）；Mayo Clinic（梅奥诊所）；Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Yale University（耶鲁大学）；University of Pennsylvania（宾夕法尼亚大学）；Arizona State University（亚利桑那州立大学）；The University of Tokyo Hospital（东京大学医院）；Carnegie Mellon University（卡内基梅隆大学）；Millennium Institute for Intelligent Healthcare Engineering (iHEALTH)（千禧年智能医疗工程研究所）；National Center for Artificial Intelligence (CENIA)（国家人工智能中心）；Xiamen University（厦门大学）；Seoul National University（首尔大学）；Rensselaer Polytechnic Institute（伦斯勒理工学院）；Institute of High Performance Computing, A*STAR（A*STAR高性能计算研究院）；Thomas Jefferson University Hospital（托马斯杰斐逊大学医院）；Massachusetts Institute of Technology（麻省理工学院）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）；Harvard T.H. Chan School of Public Health（哈佛大学陈曾熙公共卫生学院）；National Institutes of Health（美国国立卫生研究院）；National Library of Medicine（美国国家医学图书馆）
本文介绍 MICCAI 挑战赛 CXR-LT 2024，扩展大规模长尾胸部 X 光数据集并设置三项分类任务，汇总多模态、生成式与零样本方法以提升临床诊断泛化能力。
Tokyo Institute of Technology（东京工业大学）；Microsoft STCA（微软STCA）；Nanjing University（南京大学）；Microsoft Research Asia（微软亚洲研究院）
The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i.e., the model tends to classify tail classes as head classes. While existing research focused on data resampling and loss function engineering, in this paper, we take a different perspective: the classification margins. We study the relationship between the margins and logits (classification scores) and empirically observe the biased margins and the biased logits are positively correlated. We propose MARC, a simple ye…
Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification
University of Science, Ho Chi Minh City（胡志明市科学大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国立大学）；VinUni-Illinois Smart Health Center, VinUniversity（VinUni-伊利诺伊智能健康中心，Vin大学）；Carnegie Mellon University（卡内基梅隆大学）；Northwestern University（西北大学）；College of Engineering & Computer Science, VinUniversity（Vin大学工程与计算机科学学院）
Exploring "Many in Few" and "Few in Many" Properties in Long-Tailed, Highly-Imbalanced IC Defect Classification
Institute of Data Science and Information Computing, National Chung Hsing University（数据科学与信息计算研究所，中国台湾 Chung Hsing 大学）；Department of Electrical Engineering, National Tsing Hua University（电子工程系，中国台湾 Tsing Hua 大学）；Department of Electrical Engineering, National Taiwan University of Science and Technology（电子工程系，中国台湾 Science and Technology 大学）；Development of Smart Manufacturing, United Microelectronics Corporation（智能制造发展，联合微电子公司）
Multi-label text classification (MLTC) aims to annotate documents with the most relevant labels from a number of candidate labels. In real applications, the distribution of label frequency often exhibits a long tail, i.e., a few labels are associated with a large number of documents (a.k.a. head labels), while a large fraction of labels are associated with a small number of documents (a.k.a. tail labels). To address the challenge of insufficient training data on tail label classification, we propose a Head-to-Tail Network (HTTN) to transfer the meta-knowledge from the data-rich head labels to …
Real-world data universally confronts a severe class-imbalance problem and exhibits a long-tailed distribution, i.e., most labels are associated with limited instances. The naïve models supervised by such datasets would prefer dominant labels, encounter a serious generalization challenge and become poorly calibrated. We propose two novel methods from the prior perspective to alleviate this dilemma. First, we deduce a balance-oriented data augmentation named Uniform Mixup (UniMix) to promote mixup in long-tailed scenarios, which adopts advanced mixing factor and sampler in favor of the minority…
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
Institute of Information Engineering, CAS（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Tech., CAS（中国科学院计算技术研究所）；China Electronics Technology Group Corporation（中国电子科技集团公司）；Sun Yat-sen University（中山大学）
LTCI（信息与通信技术实验室）；Télécom Paris（巴黎电信学院）；Institut Polytechnique de Paris（巴黎理工学院）；IBM France（IBM法国公司）；Univ. Grenoble Alpes（格勒诺布尔大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）；LIG（信息与信号处理实验室）
The dominant approaches to text representation in natural language rely on learning embeddings on massive corpora which have convenient properties such as compositionality and distance preservation. In this paper, we develop a novel method to learn a heavy-tailed embedding with desirable regularity properties regarding the distributional tails, which allows to analyze the points far away from the distribution bulk using the framework of multivariate extreme value theory. In particular, a classifier dedicated to the tails of the proposed embedding is obtained which performance outperforms the b…
The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has questionable practicality since the target may also be long-tailed. Therefore, we formulate long-tailed visual recognition as a label shift problem where the target and source label distributions are different. One of the significant hurdles in dealing with the label shift problem is the entanglement between the source label distribution and the model prediction. I…
