Mixup

Introduced by Zhang et al. in mixup: Beyond Empirical Risk Minimization

Mixup is a data augmentation technique that that generates a weighted combinations of random image pairs from the training data. Given two images and their ground truth labels: $\left(x_{i}, y_{i}\right), \left(x_{j}, y_{j}\right)$, a synthetic training example $\left(\hat{x}, \hat{y}\right)$ is generated as:

$$ \hat{x} = \lambda{x_{i}} + \left(1 − \lambda\right){x_{j}} $$ $$ \hat{y} = \lambda{y_{i}} + \left(1 − \lambda\right){y_{j}} $$

where $\lambda \sim \text{Beta}\left(\alpha = 0.2\right)$ is independently sampled for each augmented example.

Source: mixup: Beyond Empirical Risk Minimization

Latest Papers

PAPER DATE
SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations
| Hao-Zhe FengKezhi KongMinghao ChenTianye ZhangMinfeng ZhuWei Chen
2020-11-21
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff
Eitan BorgniaValeriia CherepanovaLiam FowlAmin GhiasiJonas GeipingMicah GoldblumTom GoldsteinArjun Gupta
2020-11-18
FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
Jaemin NaHeechul JungHyungJin ChangWonjun Hwang
2020-11-18
Towards Domain-Agnostic Contrastive Learning
Vikas VermaMinh-Thang LuongKenji KawaguchiHieu PhamQuoc V. Le
2020-11-09
Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training
Dongha ChoiHyunju Lee
2020-11-04
Suppressing Mislabeled Data via Grouping and Self-Attention
Xiaojiang PengKai WangZhaoyang ZengQing LiJianfei YangYu Qiao
2020-10-29
Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
Taotao Jing NameBingrong XuJingjing LiZhengming Ding
2020-10-23
Shape-Texture Debiased Neural Network Training
| Yingwei LiQihang YuMingxing TanJieru MeiPeng TangWei ShenAlan YuilleCihang Xie
2020-10-12
Improving Low Resource Code-switched ASR using Augmented Code-switched TTS
Yash SharmaBasil AbrahamKaran TanejaPreethi Jyothi
2020-10-12
How Does Mixup Help With Robustness and Generalization?
Linjun ZhangZhun DengKenji KawaguchiAmirata GhorbaniJames Zou
2020-10-09
InstaHide: Instance-hiding Schemes for Private Distributed Learning
| Yangsibo HuangZhao SongKai LiSanjeev Arora
2020-10-06
SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup
| Rongzhi ZhangYue YuChao Zhang
2020-10-05
Mixup-Transfomer: Dynamic Data Augmentation for NLP Tasks
Lichao SunCongying XiaWenpeng YinTingTing LiangPhilip S. YuLifang He
2020-10-05
Enhancing Mixup-based Semi-Supervised Learning with Explicit Lipschitz Regularization
Prashnna Kumar GyawaliSandesh GhimireLinwei Wang
2020-09-23
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
| Jang-Hyun KimWonho ChooHyun Oh Song
2020-09-15
Webly Supervised Image Classification with Self-Contained Confidence
Jingkang YangLitong FengWeirong ChenXiaopeng YanHuabin ZhengPing LuoWayne Zhang
2020-08-27
Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training
Alfred LaugrosAlice CaplierMatthieu Ospici
2020-08-19
PointMixup: Augmentation for Point Clouds
Yunlu ChenVincent Tao HuEfstratios GavvesThomas MensinkPascal MettesPengwan YangCees G. M. Snoek
2020-08-14
Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition
| Jinpeng WangYiqi LinAndy J. Ma
2020-08-05
Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization
Yu-Ting ChangQiaosong WangWei-Chih HungRobinson PiramuthuYi-Hsuan TsaiMing-Hsuan Yang
2020-08-03
MiCo: Mixup Co-Training for Semi-Supervised Domain Adaptation
Luyu YangYan WangMingfei GaoAbhinav ShrivastavaKilian Q. WeinbergerWei-Lun ChaoSer-Nam Lim
2020-07-24
XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
Xingjian LiHaoyi XiongHaozhe AnChengzhong XuDejing Dou
2020-07-20
Uncertainty Quantification and Deep Ensembles
Rahul RahamanAlexandre H. Thiery
2020-07-17
A Machine Learning Approach to Assess Student Group Collaboration Using Individual Level Behavioral Cues
Anirudh SomSujeong KimBladimir Lopez-PradoSvati DhamijaNonye AlozieAmir Tamrakar
2020-07-13
Boundary thickness and robustness in learning models
Yaoqing YangRajiv KhannaYaodong YuAmir GholamiKurt KeutzerJoseph E. GonzalezKannan RamchandranMichael W. Mahoney
2020-07-09
Remix: Rebalanced Mixup
Hsin-Ping ChouShih-Chieh ChangJia-Yu PanWei WeiDa-Cheng Juan
2020-07-08
Dual Mixup Regularized Learning for Adversarial Domain Adaptation
Yuan WuDiana InkpenAhmed El-Roby
2020-07-07
Cross-Lingual Disaster-related Multi-label Tweet Classification with Manifold Mixup
Jishnu Ray ChowdhuryCornelia CarageaDoina Caragea
2020-07-01
Generalized Zero and Few-Shot Transfer for Facial Forgery Detection
Shivangi AnejaMatthias Nießner
2020-06-21
PatchUp: A Regularization Technique for Convolutional Neural Networks
| Mojtaba FaramarziMohammad AminiAkilesh BadrinaaraayananVikas VermaSarath Chandar
2020-06-14
Mixup Training as the Complexity Reduction
Masanari Kimura
2020-06-11
On Mixup Regularization
Luigi CarratinoMoustapha CisséRodolphe JenattonJean-Philippe Vert
2020-06-10
XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning
MyungJae ShinChihoon HwangJoongheon KimJihong ParkMehdi BennisSeong-Lyun Kim
2020-06-09
An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation
Deepan DasHaley MassaAbhimanyu KulkarniTheodoros Rekatsinas
2020-06-06
Principled learning method for Wasserstein distributionally robust optimization with local perturbations
Yongchan KwonWonyoung KimJoong-Ho WonMyunghee Cho Paik
2020-06-05
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
| Jang-Hyun KimWonho ChooHyun Oh Song
2020-06-03
Automatic classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray image: combination of data augmentation methods
Mizuho NishioShunjiro NoguchiHidetoshi MatsuoTakamichi Murakami
2020-06-01
Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning
Han ChaJihong ParkHyesung KimMehdi BennisSeong-Lyun Kim
2020-05-13
Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery
Hiroshi SasakiChris G. WillcocksToby P. Breckon
2020-05-05
Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers
Loc TruongChace JonesBrian HutchinsonAndrew AugustBrenda PraggastisRobert JasperNicole NicholsAaron Tuor
2020-04-24
YOLOv4: Optimal Speed and Accuracy of Object Detection
| Alexey BochkovskiyChien-Yao WangHong-Yuan Mark Liao
2020-04-23
ResNeSt: Split-Attention Networks
| Hang ZhangChongruo WuZhongyue ZhangYi ZhuZhi ZhangHaibin LinYue SunTong HeJonas MuellerR. ManmathaMu LiAlexander Smola
2020-04-19
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model
Dongdong WangYandong LiLiqiang WangBoqing Gong
2020-03-31
How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference
| Tai VuEmily WenRoy Nehoran
2020-03-30
Omni-sourced Webly-supervised Learning for Video Recognition
Haodong DuanYue ZhaoYuanjun XiongWentao LiuDahua Lin
2020-03-29
Self-Supervised Learning for Domain Adaptation on Point-Clouds
| Idan AchituveHaggai MaronGal Chechik
2020-03-29
Gradient-based Data Augmentation for Semi-Supervised Learning
Hiroshi Kaizuka
2020-03-28
Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
Lie JuXin WangQuan ZhouHu ZhuMehrtash HarandiPaul BonningtonTom DrummondZongyuan Ge
2020-03-23
Improving Calibration in Mixup-trained Deep Neural Networks through Confidence-Based Loss Functions
| Juan MaroñasDaniel RamosRoberto Paredes
2020-03-22
ROAM: Random Layer Mixup for Semi-Supervised Learning in Medical Imaging
Tariq BdairNassir NavabShadi Albarqouni
2020-03-20
VarMixup: Exploiting the Latent Space for Robust Training and Inference
Puneet ManglaVedant SinghShreyas Jayant HavaldarVineeth N Balasubramanian
2020-03-14
Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization
Saehyung LeeHyungyu LeeSungroh Yoon
2020-03-05
FMix: Enhancing Mixed Sample Data Augmentation
| Ethan HarrisAntonia MarcuMatthew PainterMahesan NiranjanAdam Prügel-BennettJonathon Hare
2020-02-27
Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
Bindya VenkateshJayaraman J. ThiagarajanKowshik ThopalliPrasanna Sattigeri
2020-02-10
batchboost: regularization for stabilizing training with resistance to underfitting & overfitting
| Maciej A. Czyzewski
2020-01-21
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
| Jungkyu LeeTaeryun WonTae Kwan LeeHyemin LeeGeonmo GuKiho Hong
2020-01-17
Improve Unsupervised Domain Adaptation with Mixup Training
Shen YanHuan SongNanxiang LiLincan ZouLiu Ren
2020-01-03
Big Transfer (BiT): General Visual Representation Learning
| Alexander KolesnikovLucas BeyerXiaohua ZhaiJoan PuigcerverJessica YungSylvain GellyNeil Houlsby
2019-12-24
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
Kanil PatelWilliam BeluchDan ZhangMichael PfeifferBin Yang
2019-12-16
Adversarial Domain Adaptation with Domain Mixup
| Minghao XuJian ZhangBingbing NiTeng LiChengjie WangQi TianWenjun Zhang
2019-12-04
E-Stitchup: Data Augmentation for Pre-Trained Embeddings
Cameron R. WolfeKeld T. Lundgaard
2019-11-28
Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy
Ke SunBing YuZhouchen LinZhanxing Zhu
2019-11-21
Learning Spatial Fusion for Single-Shot Object Detection
| Songtao LiuDi HuangYunhong Wang
2019-11-21
Model-agnostic Approaches to Handling Noisy Labels When Training Sound Event Classifiers
| Eduardo FonsecaFrederic FontXavier Serra
2019-10-26
Urban Sound Tagging using Convolutional Neural Networks
| Sainath Adapa
2019-09-27
Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks
| Tianyu PangKun XuJun Zhu
2019-09-25
Cross-Corpus Data Augmentation for Acoustic Addressee Detection
Oleg AkhtiamovIngo SiegertAlexey KarpovWolfgang Minker
2019-09-01
Deep Learning-Based Strategy for Macromolecules Classification with Imbalanced Data from Cellular Electron Cryotomography
Ziqian LuoXiangrui ZengZhipeng BaoMin Xu
2019-08-27
MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning
Zhijun MaiGuosheng HuDexiong ChenFumin ShenHeng Tao Shen
2019-08-27
Mish: A Self Regularized Non-Monotonic Neural Activation Function
| Diganta Misra
2019-08-23
Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation
| Egor PanfilovAleksei TiulpinStefan KleinMiika T. NieminenSimo Saarakkala
2019-08-12
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
| Eric ArazoDiego OrtegoPaul AlbertNoel E. O'ConnorKevin McGuinness
2019-08-08
Efficient Method for Categorize Animals in the Wild
| Abulikemu AbuduweiliXin WuXingchen Tao
2019-07-30
Charting the Right Manifold: Manifold Mixup for Few-shot Learning
| Puneet ManglaMayank SinghAbhishek SinhaNupur KumariVineeth N BalasubramanianBalaji Krishnamurthy
2019-07-28
Mixup of Feature Maps in a Hidden Layer for Training of Convolutional Neural Network
Hideki OkiTakio Kurita
2019-06-24
Data Interpolating Prediction: Alternative Interpretation of Mixup
Takuya ShimadaShoichiro YamaguchiKohei HayashiSosuke Kobayashi
2019-06-20
MixUp as Directional Adversarial Training
Guillaume P. ArchambaultYongyi MaoHongyu GuoRichong Zhang
2019-06-17
Suppressing Model Overfitting for Image Super-Resolution Networks
Ruicheng FengJinjin GuYu QiaoChao Dong
2019-06-11
Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples
Jake Zhao (Junbo) Kyunghyun Cho
2019-06-01
On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks
| Sunil ThulasidasanGopinath ChennupatiJeff BilmesTanmoy BhattacharyaSarah Michalak
2019-05-27
Augmenting Data with Mixup for Sentence Classification: An Empirical Study
| Hongyu GuoYongyi MaoRichong Zhang
2019-05-22
Multi-class Novelty Detection Using Mix-up Technique
Supritam BhattacharjeeDevraj MandalSoma Biswas
2019-05-11
Virtual Mixup Training for Unsupervised Domain Adaptation
| Xudong MaoYun MaZhenguo YangYangbin ChenQing Li
2019-05-10
Manifold Mixup: Learning Better Representations by Interpolating Hidden States
| Vikas VermaAlex LambChristopher BeckhamAmir NajafiAaron CourvilleIoannis MitliagkasYoshua Bengio
2019-05-01
Unsupervised Label Noise Modeling and Loss Correction
| Eric ArazoDiego OrtegoPaul AlbertNoel E. O'ConnorKevin McGuinness
2019-04-25
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
| Yunpeng ChenHaoqi FanBing XuZhicheng YanYannis KalantidisMarcus RohrbachShuicheng YanJiashi Feng
2019-04-10
CondConv: Conditionally Parameterized Convolutions for Efficient Inference
| Brandon YangGabriel BenderQuoc V. LeJiquan Ngiam
2019-04-10
Kernel-Free Image Deblurring with a Pair of Blurred/Noisy Images
Chunzhi GuXuequan LuYing HeChao Zhang
2019-03-26
Manifold Mixup improves text recognition with CTC loss
Bastien MoyssetRonaldo Messina
2019-03-11
Bag of Tricks for Image Classification with Convolutional Neural Networks
| Tong HeZhi ZhangHang ZhangZhongyue ZhangJunyuan XieMu Li
2018-12-04
Generalization Bounds for Vicinal Risk Minimization Principle
Chao ZhangMin-Hsiu HsiehDacheng Tao
2018-11-11
Label Denoising with Large Ensembles of Heterogeneous Neural Networks
Pavel OstyakovElizaveta LogachevaRoman SuvorovVladimir AlievGleb SterkinOleg KhomenkoSergey I. Nikolenko
2018-09-12
MixUp as Locally Linear Out-Of-Manifold Regularization
| Hongyu GuoYongyi MaoRichong Zhang
2018-09-07
Manifold Mixup: Better Representations by Interpolating Hidden States
| Vikas VermaAlex LambChristopher BeckhamAmir NajafiIoannis MitliagkasAaron CourvilleDavid Lopez-PazYoshua Bengio
2018-06-13
Mixup-Based Acoustic Scene Classification Using Multi-Channel Convolutional Neural Network
Kele XuDawei FengHaibo MiBoqing ZhuDezhi WangLilun ZhangHengxing CaiShuwen Liu
2018-05-18
Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples
Jake ZhaoKyunghyun Cho
2018-02-26
mixup: Beyond Empirical Risk Minimization
| Hongyi ZhangMoustapha CisseYann N. DauphinDavid Lopez-Paz
2017-10-25

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories