Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. However, the effective integration of T2I models into fundamental image classification tasks remains an open question. A prevalent strategy to bolster image classification performance is through augmenting the training set with synthetic images generated by T2I models. In this study, we scrutinize the shortcomings of both current generative and conventional data augmentation techniques. Our analysis reveals that these methods struggle to produce images that are both faithful (in terms of foreground objects) and diverse (in terms of background contexts) for domain-specific concepts. To tackle this challenge, we introduce an innovative inter-class data augmentation method known as Diff-Mix (https://github.com/Zhicaiwww/Diff-Mix), which enriches the dataset by performing image translations between classes. Our empirical results demonstrate that Diff-Mix achieves a better balance between faithfulness and diversity, leading to a marked improvement in performance across diverse image classification scenarios, including few-shot, conventional, and long-tail classifications for domain-specific datasets.
Seoul National University（首尔国立大学）；NAVER WEBTOON AI（NAVER WEBTOON人工智能研究院）
Producing diverse and realistic images with generative models such as GANs typically requires large scale training with vast amount of images. GANs trained with limited data can easily memorize few training samples and display undesirable properties like "stairlike" latent space where interpolation in the latent space yields discontinuous transitions in the output space. In this work, we consider a challenging task of pretraining-free few-shot image synthesis, and seek to train existing generative models with minimal overfitting and mode collapse. We propose mixup-based distance regularization…
Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels. Many recent mixup methods focus on cutting and pasting two or more objects into one image, which is more about efficient processing than interpolation. However, how to best interpolate images is not well defined. In this sense, mixup has been connected to autoencoders, because often autoencoders "interpolate well", for instance generating an image that continuously deforms into another. In this work, we revisit mixup from the int…
Modern handwritten text recognition techniques employ deep recurrent neural networks. The use of these techniques is especially efficient when a large amount of annotated data is available for parameter estimation. Data augmentation can be used to enhance the performance of the systems when data is scarce. Manifold Mixup is a modern method of data augmentation that meld two images or the feature maps corresponding to these images and the targets are fused accordingly. We propose to apply the Manifold Mixup to text recognition while adapting it to work with a Connectionist Temporal Classificati…
Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model. Knowledge distillation (KD), on the other hand, is widely used for model compression and transfer learning, which involves using a larger network's implicit knowledge to guide the learning of a smaller network. At first glance, these two techniques seem very different, however, we found that "smoothness" is the connecting link between the two and is also a crucial attribute in understanding K…
Biometrics Research Laboratories, NEC（NEC生物识别研究实验室）
It is well-known that training of generative adversarial networks (GANs) requires huge iterations before the generator's providing good-quality samples. Although there are several studies to tackle this problem, there is still no universal solution. In this paper, we investigated the effect of sample mixing methods, that is, Mixup, CutMix, and newly proposed Smoothed Regional Mix (SRMix), to alleviate this problem. The sample-mixing methods are known to enhance the accuracy and robustness in the wide range of classification problems, and can naturally be applicable to GANs because the role of …
Technical University of Munich（慕尼黑工业大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；ETH Zurich（苏黎世联邦理工学院）
Medical image segmentation is one of the major challenges addressed by machine learning methods. Yet, deep learning methods profoundly depend on a large amount of annotated data, which is time-consuming and costly. Though, semi-supervised learning methods approach this problem by leveraging an abundant amount of unlabeled data along with a small amount of labeled data in the training process. Recently, MixUp regularizer has been successfully introduced to semi-supervised learning methods showing superior performance. MixUp augments the model with new data points through linear interpolation of…
FIXED: Frustratingly Easy Domain Generalization with Mixup
Tsinghua University（清华大学）；Microsoft（微软）；Nanyang Technological University（南洋理工大学）；University of North Carolina（北卡罗来纳大学）；University of Chinese Academy of Sciences（中国科学院大学）
Given sufficient training data on the source domain, cross-domain few-shot learning (CD-FSL) aims at recognizing new classes with a small number of labeled examples on the target domain. The key to addressing CD-FSL is to narrow the domain gap and transferring knowledge of a network trained on the source domain to the target domain. To help knowledge transfer, this paper introduces an intermediate domain generated by mixing images in the source and the target domain. Specifically, to generate the optimal intermediate domain for different target data, we propose a novel target guided dynamic mi…
Simon Fraser University（西蒙弗雷泽大学）；Hinge Health（Hinge Health公司）
Modern deep learning training procedures rely on model regularization techniques such as data augmentation methods, which generate training samples that increase the diversity of data and richness of label information. A popular recent method, mixup, uses convex combinations of pairs of original samples to generate new samples. However, as we show in our experiments, mixup can produce undesirable synthetic samples, where the data is sampled off the manifold and can contain incorrect labels. We propose $ζ$-mixup, a generalization of mixup with provably and demonstrably desirable properties that…
Tencent（腾讯）；Tsinghua University（清华大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models often largely degrade on testing data which is unseen and Out-Of-the-Distribution (OOD). To address this issue, we propose a novel "Decoupled-Mixup" method to train CNN models for OOD visual recognition. Different from previous work combining pairs of images homogeneously, our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combines these regions of image pairs to train …
BGM: Background Mixup for X-ray Prohibited Items Detection
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学学院）；Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Nuctech Company Limited（核tech公司）
针对 X 射线安检检测忽视背景信息的问题，提出基于透射成像与材料伪彩色特性的 Background Mixup 背景增强，可兼容前景增强并在多个基准上稳定提升性能。
University of Bristol（布里斯托大学）；Singapore Management University（新加坡管理大学）；Fudan University（复旦大学）；City University of Hong Kong（香港城市大学）
Cross-modal recipe retrieval has attracted research attention in recent years, thanks to the availability of large-scale paired data for training. Nevertheless, obtaining adequate recipe-image pairs covering the majority of cuisines for supervised learning is difficult if not impossible. By transferring knowledge learnt from a data-rich cuisine to a data-scarce cuisine, domain adaptation sheds light on this practical problem. Nevertheless, existing works assume recipes in source and target domains are mostly originated from the same cuisine and written in the same language. This paper studies …
University of Science and Technology of China（中国科学技术大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images. In this work, we propose a novel modality-adaptive mixup and invariant decomposition (MID) approach for RGB-infrared person re-identification towards learning modality-invariant and discriminative representations. MID designs a modality-adaptive mixup scheme to generate suitable mixed modality images between RGB and infrared images for mitigating the inherent modality discrepancy at the pixel-level. It for…
Improving Mixup Calibration with Wasserstein Distributionally Robust Optimization
Department of Mathematics & Statistics（数学与统计学系）；Boston University（波士顿大学）；Department of Electrical and Computer Engineering, Division of Systems Engineering（电气与计算机工程系，系统工程 division）；Department of Biomedical Engineering（生物医学工程系）；Faculty of Computing & Data Sciences（计算与数据科学学院）
Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not always available due to the privacy preserving consideration or bandwidth limitation. Source-free domain adaptation aims to solve the above problem by performing domain adaptation without accessing the source data. The adaptation paradigm is receiving more and more attention in recent years, and multiple works have been proposed for unsupervised source-free domain adaptation. However, without utilizing any supervised s…
Mixup is a procedure for data augmentation that trains networks to make smoothly interpolated predictions between datapoints. Adversarial training is a strong form of data augmentation that optimizes for worst-case predictions in a compact space around each data-point, resulting in neural networks that make much more robust predictions. In this paper, we bring these ideas together by adversarially probing the space between datapoints, using projected gradient descent (PGD). The fundamental approach in this work is to leverage backpropagation through the mixup interpolation during training to o…
A Multi-Stage Deep Learning Framework with PKCP-MixUp Augmentation for Pediatric Liver Tumor Diagnosis Using Multi-Phase Contrast-Enhanced CT
Wuhan Children's Hospital (Wuhan Maternal and Child Healthcare Hospital), Tongji Medical College, Huazhong University of Science and Technology（华中科技大学同济医学院武汉儿童医院（武汉市妇幼保健院））；Wuhan University（武汉大学）；Wuhan Cloud Computing Technology Co., Ltd.（武汉云计算技术有限公司）
Ryerson University（瑞尔森大学）；Vector Institute（矢量研究院）；Samsung AI Centre（三星人工智能中心）；University of Guelph（圭尔夫大学）
In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical information throughout the network. The premise is based on the notion of feature binding, which is defined as the process by which activation's spread across space and layers in the network are successfully integrated to arrive at a correct inference decision. In our work, this is accomplished for the task of dense image labelling by blending images based on their class labels, and then training a feature binding ne…
Environmental sound analysis is currently getting more and more attentions. In the domain, acoustic scene classification and acoustic event classification are two closely related tasks. In this letter, a two-stage method is proposed for the above tasks. In the first stage, a mixup based MTL solution is proposed to classify both tasks in one single convolutional neural network. Artificial multi-label samples are used in the training of the MTL model, which are mixed up using existing single-task datasets. The multi-task model obtained can effectively recognize both the acoustic scenes and event…
Zhejiang University（浙江大学）；University of Notre Dame（圣母大学）
In clinical practice, medical image interpretation often involves multi-labeled classification, since the affected parts of a patient tend to present multiple symptoms or comorbidities. Recently, deep learning based frameworks have attained expert-level performance on medical image interpretation, which can be attributed partially to large amounts of accurate annotations. However, manually annotating massive amounts of medical images is impractical, while automatic annotation is fast but imprecise (possibly introducing corrupted labels). In this work, we propose a new regularization approach, …
Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency information to match the mixed samples and labels via complex offline optimization. However, there arises a trade-off between precise mixing policies and optimization complexity. To address this challenge, we propose a novel automatic mixup (AutoMix) framework, where the mixup policy is parameterized and serves the ultimate classification goal directly. Specifi…
Beyond Dark Knowledge: Mixup-Based Distillation for Reliable Predictions
ITS Lab, Institute of Computer Science, University of Tartu（塔尔图大学计算机科学学院ITS实验室）；LITIS, Université de Rouen（鲁昂大学LITIS实验室）；LITIS, INSA de Rouen（鲁昂国立应用科学学院LITIS实验室）
Ryerson University（瑞尔森大学）；Vector Institute for AI（向量人工智能研究所）；York University（约克大学）；Samsung AI Research Center Toronto（三星多伦多人工智能研究中心）；University of Guelph（圭尔夫大学）
In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical information throughout the network. The premise is based on the notion of feature binding, which is defined as the process by which activations spread across space and layers in the network are successfully integrated to arrive at a correct inference decision. In our work, this is accomplished for the task of dense image labelling by blending images based on (i) categorical clustering or (ii) the co-occurrence likeli…
Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing
Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin（电气工程与计算机科学学院，柏林技术大学）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）
ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentation
The Hong Kong Polytechnic University（香港理工大学）；Southern University of Science and Technology（南方科技大学）；Research Institute of Trustworthy Autonomous Systems（可信自主系统研究院）
Peking University（北京大学）；Chongqing University of Technology（重庆理工大学）；Peng Cheng Laboratory（鹏城实验室）
The performance of existing underwater object detection methods degrades seriously when facing domain shift caused by complicated underwater environments. Due to the limitation of the number of domains in the dataset, deep detectors easily memorize a few seen domains, which leads to low generalization ability. There are two common ideas to improve the domain generalization performance. First, it can be inferred that the detector trained on as many domains as possible is domain-invariant. Second, for the images with the same semantic content in different domains, their hidden features should be…
MixUp-MIL: A Study on Linear & Multilinear Interpolation-Based Data Augmentation for Whole Slide Image Classification
Salzburg University of Applied Sciences（萨尔茨堡应用科学大学）；Spinal Cord Injury and Tissue Regeneration Center Salzburg（萨尔茨堡脊髓损伤与组织再生中心）；Research Institute of Experimental Neuroregeneration（实验神经再生研究所）；Kardinal Schwarzenberg Klinikum（红衣主教施瓦岑贝格医院）
MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer Diagnosis
Salzburg University of Applied Sciences（萨尔茨堡应用科学大学）；Spinal Cord Injury and Tissue Regeneration Center Salzburg（萨尔茨堡脊髓损伤与组织再生中心）；Research Institute of Experimental Neuroregeneration（实验神经再生研究所）；Kardinal Schwarzenberg Klinikum（红衣主教施瓦岑贝格医院）
Seoul National University（首尔国立大学）；Neural Processing Research Center（神经处理研究中心）
While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks. In this regard, a number of mixup based augmentation methods have been recently proposed. However, these approaches mainly focus on creating previously unseen virtual examples and can sometimes provide misleading supervisory signal to the network. To this end, we propose Puzzle Mix, a mixup method for explicitly utilizing the saliency information and the underlying statistics of the natural examples. This leads to a…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）；Sun Yat-sen University（中山大学）；Southwest Jiaotong University（西南交通大学）；Nanyang Technological University（南洋理工大学）
Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this paper proposes a conceptually simple yet efficient training block, termed as Attentive Feature Mixup (AFM), which allows paying more attention to clean samples and less to mislabeled ones via sample interactions in small groups. Specifically, this plug-and-play AFM first leverages a \textit{group-to-attend} module to construct groups and assign attention weights for group-wise samples, and then uses a \textit{mixup} modu…
University of California, Merced（加州大学默塞德分校）；eBay Inc.（eBay公司）；NEC Labs America（美国NEC实验室）；Google Research（谷歌研究院）
Obtaining object response maps is one important step to achieve weakly-supervised semantic segmentation using image-level labels. However, existing methods rely on the classification task, which could result in a response map only attending on discriminative object regions as the network does not need to see the entire object for optimizing the classification loss. To tackle this issue, we propose a principled and end-to-end train-able framework to allow the network to pay attention to other parts of the object, while producing a more complete and uniform response map. Specifically, we introdu…
Image classification with deep neural networks has seen a surge of technological breakthroughs with promising applications in areas such as face recognition, medical imaging, and autonomous driving. In engineering problems, however, such as high-speed imaging of engine fuel injector sprays or body paint sprays, deep neural networks face a fundamental challenge related to the availability of adequate and diverse data. Typically, only thousands or sometimes even hundreds of samples are available for training. In addition, the transition between different spray classes is a continuum and requires…
Anhui University（安徽大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Science and Technology of China（中国科学技术大学）
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Owing to privacy concerns and heavy data transmission, source-free UDA, exploiting the pre-trained source models instead of the raw source data for target learning, has been gaining popularity in recent years. Some works attempt to recover unseen source domains with generative models, however introducing additional network parameters. Other works propose to fine-tune the source model by pseudo labels, while noisy pseudo labels may misguide the decision boundary, leading t…
Saliency-guided and Patch-based Mixup for Long-tailed Skin Cancer Image Classification
Southern University of Science and Technology（南方科技大学）；University of British Columbia（不列颠哥伦比亚大学）；The University of Hong Kong（香港大学）；Jiaxing Research Institute, Southern University of Science and Technology（南方科技大学嘉兴研究院）
