Methods › Computer Vision › Image Data Augmentation › Mixup
Mixup
Introduced by Hongyi Zhang et al. in mixup: Beyond Empirical Risk Minimization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels: (xᵢ, yᵢ), (xⱼ, yⱼ), a synthetic training example (x̂, ŷ) is generated as:
x̂ = λxᵢ + (1 − λ)xⱼ ŷ = λyᵢ + (1 − λ)yⱼ
where λ∼Beta(α= 0.2) is independently sampled for each augmented example.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 71 in the graph, strongest link: official). The lookup matched 'mixup' ignoring case. This answer is about arXiv:1710.09412, the paper the archive credits with this method.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- C-Mixup · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='C-Mixup') - Weight Mixup · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Weight Mixup')
Origin paper of this answer, arXiv:1710.09412 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified (of 47 harvested samples) · 15 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 651 · with a code link: 308 · where Syntology ran a sample: 89 (74 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (89 of 651 tagged: 74 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument)
Page 1 of 7: papers 1 to 100 of 651, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing 26 Jun 2025 · 0 repositories · arXiv:2506.21312
-
Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation 25 Jun 2025 · 0 repositories · arXiv:2506.20867
-
Quantum-Informed Contrastive Learning with Dynamic Mixup Augmentation for Class-Imbalanced Expert Systems 16 Jun 2025 · 0 repositories · arXiv:2506.13987
-
MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions 11 Jun 2025 · 1 repository · arXiv:2506.09556
-
Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation 30 May 2025 · 1 repository · arXiv:2505.24567
-
BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models 23 May 2025 · 2 repositories · arXiv:2505.17871Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action Recognition 23 May 2025 · 1 repository · arXiv:2505.17807
-
Cross-Domain Diffusion with Progressive Alignment for Efficient Adaptive Retrieval 20 May 2025 · 0 repositories · arXiv:2505.13907
-
Suicide Risk Assessment Using Multimodal Speech Features: A Study on the SW1 Challenge Dataset 19 May 2025 · 0 repositories · arXiv:2505.13069
-
SAINT: Attention-Based Modeling of Sub-Action Dependencies in Multi-Action Policies 17 May 2025 · 1 repository · arXiv:2505.12109
-
Data-Agnostic Augmentations for Unknown Variations: Out-of-Distribution Generalisation in MRI Segmentation 15 May 2025 · 1 repository · arXiv:2505.10223
-
UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing 14 May 2025 · 1 repository · arXiv:2505.09615
-
GradMix: Gradient-based Selective Mixup for Robust Data Augmentation in Class-Incremental Learning 13 May 2025 · 0 repositories · arXiv:2505.08528
-
MediAug: Exploring Visual Augmentation in Medical Imaging 26 Apr 2025 · 1 repository · arXiv:2504.18983
-
AMAD: AutoMasked Attention for Unsupervised Multivariate Time Series Anomaly Detection 9 Apr 2025 · 0 repositories · arXiv:2504.06643
-
mixEEG: Enhancing EEG Federated Learning for Cross-subject EEG Classification with Tailored mixup 7 Apr 2025 · 1 repository · arXiv:2504.07987
-
iADCPS: Time Series Anomaly Detection for Evolving Cyber-physical Systems via Incremental Meta-learning 6 Apr 2025 · 0 repositories · arXiv:2504.04374
-
Enlightenment Period Improving DNN Performance 2 Apr 2025 · 0 repositories · arXiv:2504.01737
-
ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation 31 Mar 2025 · 0 repositories · arXiv:2503.23712
-
Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation 27 Mar 2025 · 1 repository · arXiv:2503.21140
-
V2X-DG: Domain Generalization for Vehicle-to-Everything Cooperative Perception 19 Mar 2025 · 0 repositories · arXiv:2503.15435
-
Similarity-Aware Token Pruning: Your VLM but Faster 14 Mar 2025 · 1 repository · arXiv:2503.11549
-
Class-Aware PillarMix: Can Mixed Sample Data Augmentation Enhance 3D Object Detection with Radar Point Clouds? 4 Mar 2025 · 0 repositories · arXiv:2503.02687
-
Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixup 4 Mar 2025 · 0 repositories · arXiv:2503.02284
-
A Generalized Theory of Mixup for Structure-Preserving Synthetic Data 3 Mar 2025 · 1 repository · arXiv:2503.02645
-
MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition 28 Feb 2025 · 0 repositories · arXiv:2503.00202
-
Single Domain Generalization with Model-aware Parametric Batch-wise Mixup 22 Feb 2025 · 0 repositories · arXiv:2502.16064
-
Mixup Model Merge: Enhancing Model Merging Performance through Randomized Linear Interpolation 21 Feb 2025 · 1 repository · arXiv:2502.15434
-
TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation 20 Feb 2025 · 0 repositories · arXiv:2502.15016
-
Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks 19 Feb 2025 · 1 repository · arXiv:2502.14158
-
Mixup Regularization: A Probabilistic Perspective 19 Feb 2025 · 0 repositories · arXiv:2502.13825
-
Towards Understanding Why Data Augmentation Improves Generalization 13 Feb 2025 · 0 repositories · arXiv:2502.08940
-
ASCenD-BDS: Adaptable, Stochastic and Context-aware framework for Detection of Bias, Discrimination and Stereotyping 4 Feb 2025 · 0 repositories · arXiv:2502.02072
-
Role of Mixup in Topological Persistence Based Knowledge Distillation for Wearable Sensor Data 2 Feb 2025 · 0 repositories · arXiv:2502.00779
-
Contrastive Learning Meets Pseudo-label-assisted Mixup Augmentation: A Comprehensive Graph Representation Framework from Local to Global 30 Jan 2025 · 0 repositories · arXiv:2501.18357
-
VoicePrompter: Robust Zero-Shot Voice Conversion with Voice Prompt and Conditional Flow Matching 29 Jan 2025 · 0 repositories · arXiv:2501.17612
-
TdAttenMix: Top-Down Attention Guided Mixup 26 Jan 2025 · 1 repository · arXiv:2501.15409
-
Towards Robust Unsupervised Attention Prediction in Autonomous Driving 25 Jan 2025 · 1 repository · arXiv:2501.15045
-
Enhancing Medical Image Analysis through Geometric and Photometric transformations 23 Jan 2025 · 0 repositories · arXiv:2501.13643
-
pMixFed: Efficient Personalized Federated Learning through Adaptive Layer-Wise Mixup 19 Jan 2025 · 0 repositories · arXiv:2501.11002
-
Linearly Convergent Mixup Learning 14 Jan 2025 · 0 repositories · arXiv:2501.07794
-
Continual Self-supervised Learning Considering Medical Domain Knowledge in Chest CT Images 8 Jan 2025 · 0 repositories · arXiv:2501.04217
-
AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation 4 Jan 2025 · 0 repositories · arXiv:2501.02182
-
Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptation 2 Jan 2025 · 0 repositories · arXiv:2501.01126
-
FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing 1 Jan 2025 · 0 repositories
-
Generative Hard Example Augmentation for Semantic Point Cloud Segmentation 1 Jan 2025 · 0 repositories
-
Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classification 29 Dec 2024 · 0 repositories · arXiv:2501.00064
-
Generative Regression Based Watch Time Prediction for Short-Video Recommendation 28 Dec 2024 · 0 repositories · arXiv:2412.20211
-
Spectral-Temporal Fusion Representation for Person-in-Bed Detection 27 Dec 2024 · 0 repositories · arXiv:2412.19404
-
Computational Analysis of Yaredawi YeZema Silt in Ethiopian Orthodox Tewahedo Church Chants 25 Dec 2024 · 1 repository · arXiv:2412.18788
-
LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning 22 Dec 2024 · 1 repository · arXiv:2412.16963
-
FairDD: Enhancing Fairness with domain-incremental learning in dermatological disease diagnosis 21 Dec 2024 · 0 repositories · arXiv:2412.16542
-
Head and Neck Tumor Segmentation of MRI from Pre- and Mid-radiotherapy with Pre-training, Data Augmentation and Dual Flow UNet 19 Dec 2024 · 1 repository · arXiv:2412.14846
-
Cluster-guided Contrastive Class-imbalanced Graph Classification 17 Dec 2024 · 0 repositories · arXiv:2412.12984
-
Three Things to Know about Deep Metric Learning 17 Dec 2024 · 0 repositories · arXiv:2412.12432
-
RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning 14 Dec 2024 · 0 repositories · arXiv:2412.10741
-
Who's the (Multi-)Fairest of Them All: Rethinking Interpolation-Based Data Augmentation Through the Lens of Multicalibration 13 Dec 2024 · 1 repository · arXiv:2412.10575
-
DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain Generalization 12 Dec 2024 · 1 repository · arXiv:2412.09074
-
AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification 11 Dec 2024 · 1 repository · arXiv:2412.08144
-
UNCOVER: Unknown Class Object Detection for Autonomous Vehicles in Real-time 5 Dec 2024 · 0 repositories · arXiv:2412.03986
-
MeasureNet: Measurement Based Celiac Disease Identification 2 Dec 2024 · 0 repositories · arXiv:2412.01182
-
BGM: Background Mixup for X-ray Prohibited Items Detection 30 Nov 2024 · 0 repositories · arXiv:2412.00460
-
Improving Transferable Targeted Attacks with Feature Tuning Mixup 23 Nov 2024 · 1 repository · arXiv:2411.15553
-
Learning Fair Robustness via Domain Mixup 21 Nov 2024 · 0 repositories · arXiv:2411.14424
-
Out-Of-Distribution Detection with Diversification (Provably) 21 Nov 2024 · 1 repository · arXiv:2411.14049Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 12 pointer-only (licence)
-
Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition 12 Nov 2024 · 0 repositories · arXiv:2411.07621
-
Learning from Different Samples: A Source-free Framework for Semi-supervised Domain Adaptation 11 Nov 2024 · 0 repositories · arXiv:2411.06665
-
Adaptive Aspect Ratios with Patch-Mixup-ViT-based Vehicle ReID 9 Nov 2024 · 1 repository · arXiv:2411.06297
-
Heterogeneous Interaction Modeling With Reduced Accumulated Error for Multi-Agent Trajectory Prediction 28 Oct 2024 · 0 repositories · arXiv:2410.21342
-
Mitigating Graph Covariate Shift via Score-based Out-of-distribution Augmentation 23 Oct 2024 · 0 repositories · arXiv:2410.17506
-
AC-Mix: Self-Supervised Adaptation for Low-Resource Automatic Speech Recognition using Agnostic Contrastive Mixup 18 Oct 2024 · 0 repositories · arXiv:2410.14910
-
A Survey on Deep Tabular Learning 15 Oct 2024 · 0 repositories · arXiv:2410.12034
-
A few-shot Label Unlearning in Vertical Federated Learning 14 Oct 2024 · 0 repositories · arXiv:2410.10922
-
Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective 5 Oct 2024 · 0 repositories · arXiv:2410.03999
-
DyMix: Dynamic Frequency Mixup Scheduler based Unsupervised Domain Adaptation for Enhancing Alzheimer's Disease Identification 2 Oct 2024 · 0 repositories · arXiv:2410.12827
-
ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups 2 Oct 2024 · 0 repositories · arXiv:2410.01145
-
Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification 26 Sep 2024 · 1 repository · arXiv:2409.17777
-
Region Mixup 23 Sep 2024 · 0 repositories · arXiv:2409.15028
-
Robust Audio-Visual Speech Enhancement: Correcting Misassignments in Complex Environments with Advanced Post-Processing 22 Sep 2024 · 0 repositories · arXiv:2409.14554
-
Data Efficient Acoustic Scene Classification using Teacher-Informed Confusing Class Instruction 18 Sep 2024 · 0 repositories · arXiv:2409.11964
-
Test-time Training for Hyperspectral Image Super-resolution 13 Sep 2024 · 0 repositories · arXiv:2409.08667
-
A Survey on Mixup Augmentations and Beyond 8 Sep 2024 · 1 repository · arXiv:2409.05202
-
Text-Guided Mixup Towards Long-Tailed Image Categorization 5 Sep 2024 · 1 repository · arXiv:2409.03583
-
MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent Imputation 11 Aug 2024 · 1 repository · arXiv:2408.05740
-
Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion 4 Aug 2024 · 0 repositories · arXiv:2408.02695
-
PreMix: Addressing Label Scarcity in Whole Slide Image Classification with Pre-trained Multiple Instance Learning Aggregators 2 Aug 2024 · 0 repositories · arXiv:2408.01162
-
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning 16 Jul 2024 · 1 repository · arXiv:2407.12188
-
Rethinking Fair Graph Neural Networks from Re-balancing 16 Jul 2024 · 1 repository · arXiv:2407.11624Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 2 pointer-only (licence)
-
GeoMix: Towards Geometry-Aware Data Augmentation 15 Jul 2024 · 1 repository · arXiv:2407.10681
-
Study on Aspect Ratio Variability toward Robustness of Vision Transformer-based Vehicle Re-identification 10 Jul 2024 · 0 repositories · arXiv:2407.07842
-
SUMix: Mixup with Semantic and Uncertain Information 10 Jul 2024 · 2 repositories · arXiv:2407.07805Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 2 pointer-only (licence)
-
Invariance Principle Meets Vicinal Risk Minimization 8 Jul 2024 · 0 repositories · arXiv:2407.05765
-
A Pairwise DomMix Attentive Adversarial Network for Unsupervised Domain Adaptive Object Detection 3 Jul 2024 · 0 repositories · arXiv:2407.02835
-
Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment 22 Jun 2024 · 0 repositories · arXiv:2406.15723
-
Edge Classification on Graphs: New Directions in Topological Imbalance 17 Jun 2024 · 1 repository · arXiv:2406.11685
-
First-Order Manifold Data Augmentation for Regression Learning 16 Jun 2024 · 1 repository · arXiv:2406.10914Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples)
-
CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecasting 8 Jun 2024 · 1 repository · arXiv:2406.05316Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 2 pointer-only (licence)
-
Mixup Augmentation with Multiple Interpolations 3 Jun 2024 · 0 repositories · arXiv:2406.01417
-
GenMix: Combining Generative and Mixture Data Augmentation for Medical Image Classification 31 May 2024 · 0 repositories · arXiv:2405.20650
-
RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression Tasks 28 May 2024 · 0 repositories · arXiv:2405.17938
Tasks archive 2025-07-28
20 shown of 424 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections