AutoAugment: Learning Augmentation Policies from Data
arXiv:1805.09501
Abstract
Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch. A sub-policy consists of two operations, each operation being an image processing function such as translation, rotation, or shearing, and the probabilities and magnitudes with which the functions are applied. We use a search algorithm to find the best policy such that the neural network yields the highest validation accuracy on a target dataset. Our method achieves state-of-the-art accuracy on CIFAR-10, CIFAR-100, SVHN, and ImageNet (without additional data). On ImageNet, we attain a Top-1 accuracy of 83.5% which is 0.4% better than the previous record of 83.1%. On CIFAR-10, we achieve an error rate of 1.5%, which is 0.6% better than the previous state-of-the-art. Augmentation policies we find are transferable between datasets. The policy learned on ImageNet transfers well to achieve significant improvements on other datasets, such as Oxford Flowers, Caltech-101, Oxford-IIT Pets, FGVC Aircraft, and Stanford Cars.
arXiv commentCVPR 2019
References in corpus (35)
- mixup: Beyond Empirical Risk Minimization
- Neural Architecture Search with Reinforcement Learning
- Neural Message Passing for Quantum Chemistry
- Improved Regularization of Convolutional Neural Networks with Cutout
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- Wide Residual Networks
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Temporal Ensembling for Semi-Supervised Learning
- Going Deeper with Convolutions
- Fine-Grained Visual Classification of Aircraft
- Data Augmentation Generative Adversarial Networks
- Random Erasing Data Augmentation
- Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
- Smart Augmentation - Learning an Optimal Data Augmentation Strategy
- SMASH: One-Shot Model Architecture Search through HyperNetworks
- Aggregated Residual Transformations for Deep Neural Networks
- Some Improvements on Deep Convolutional Neural Network Based Image Classification
- Data Augmentation by Pairing Samples for Images Classification
- Shake-Shake regularization
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
- Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
- Neural Optimizer Search with Reinforcement Learning
- ShakeDrop Regularization for Deep Residual Learning
- Simple And Efficient Architecture Search for Convolutional Neural Networks
- Progressive Neural Architecture Search
- Simple random search provides a competitive approach to reinforcement learning
- The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems
- Do CIFAR-10 Classifiers Generalize to CIFAR-10?
- A Bayesian Data Augmentation Approach for Learning Deep Models
- APAC: Augmented PAttern Classification with Neural Networks
- Data Augmentation in Emotion Classification Using Generative Adversarial Networks
- Deep Layer Aggregation
- Intriguing Properties of Adversarial Examples
- Parallel Architecture and Hyperparameter Search via Successive Halving and Classification
Cited by in corpus (334)
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Generative Adversarial Network in Medical Imaging: A Review
- Neural Architecture Search: A Survey
- Unsupervised Data Augmentation for Consistency Training
- MLP-Mixer: An all-MLP Architecture for Vision
- Training Generative Adversarial Networks with Limited Data
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- Generalizing from a Few Examples: A Survey on Few-Shot Learning
- Solving Rubik's Cube with a Robot Hand
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- Data Augmentation using Random Image Cropping and Patching for Deep CNNs
- Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
- Do ImageNet Classifiers Generalize to ImageNet?
- Rethinking Pre-training and Self-training
- Early Convolutions Help Transformers See Better
- Billion-scale semi-supervised learning for image classification
- Out-of-Distribution Generalization via Risk Extrapolation (REx)
- DARTS+: Improved Differentiable Architecture Search with Early Stopping
- GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
- Machine-Learning-Based Diagnostics of EEG Pathology
- Revisiting ResNets: Improved Training and Scaling Strategies
- A Survey on Neural Architecture Search
- High Quality Monocular Depth Estimation via Transfer Learning
- Quantifying Generalization in Reinforcement Learning
- On Empirical Comparisons of Optimizers for Deep Learning
- Measuring Robustness to Natural Distribution Shifts in Image Classification
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
- Improving robustness against common corruptions by covariate shift adaptation
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
- A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspective
- Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples
- Adversarial Examples Are a Natural Consequence of Test Error in Noise
- AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
- Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
- Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
- NAS evaluation is frustratingly hard
- Fixing Data Augmentation to Improve Adversarial Robustness
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
- The Conditional Entropy Bottleneck
- Differentiable Augmentation for Data-Efficient GAN Training
- Label-Only Membership Inference Attacks
- Smooth Adversarial Training
- Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
- Best Practices for Scientific Research on Neural Architecture Search
- A Fourier Perspective on Model Robustness in Computer Vision
- AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
- Selfie: Self-supervised Pretraining for Image Embedding
- Unlabeled Data Improves Adversarial Robustness
- Fixing the train-test resolution discrepancy: FixEfficientNet
- ASAP: Architecture Search, Anneal and Prune
- Rethinking the Hyperparameters for Fine-tuning
- ConTNet: Why not use convolution and transformer at the same time?
- Soft Contextual Data Augmentation for Neural Machine Translation
- Data augmentation using learned transformations for one-shot medical image segmentation
- Small Sample Learning in Big Data Era
- i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
- Dataset Condensation with Differentiable Siamese Augmentation
- Affinity and Diversity: Quantifying Mechanisms of Data Augmentation
- Multi-Sample Dropout for Accelerated Training and Better Generalization
- Augment your batch: better training with larger batches
- MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
- Adversarial Examples Improve Image Recognition
- An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition
- Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
- Reinforcement Learning Applications
- Skin Lesions Classification Using Convolutional Neural Networks in Clinical Images
- Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks
- Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
- Optimizing Millions of Hyperparameters by Implicit Differentiation
- AtomNAS: Fine-Grained End-to-End Neural Architecture Search
- FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
- ReSSL: Relational Self-Supervised Learning with Weak Augmentation
- Sampling Strategies for GAN Synthetic Data
- ResizeMix: Mixing Data with Preserved Object Information and True Labels
- BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
- Ensemble learning in CNN augmented with fully connected subnetworks
- Noisy Differentiable Architecture Search
- Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation
- Contrastive Learning with Stronger Augmentations
- Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
- An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
- sharpDARTS: Faster and More Accurate Differentiable Architecture Search
- Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
- DeepLab2: A TensorFlow Library for Deep Labeling
- MultiGrain: a unified image embedding for classes and instances
- MaxUp: A Simple Way to Improve Generalization of Neural Network Training
- Adversarial Examples Make Strong Poisons
- ResNet strikes back: An improved training procedure in timm
- An embedded system for the automated generation of labeled plant images to enable machine learning applications in agriculture
- Data-Efficient Instance Generation from Instance Discrimination
- DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
- Regularizing Class-wise Predictions via Self-knowledge Distillation
- Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search
- GOLD-NAS: Gradual, One-Level, Differentiable
- Large-Scale Generative Data-Free Distillation
- Using Videos to Evaluate Image Model Robustness
- Scaling Wide Residual Networks for Panoptic Segmentation
- CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
- Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
- Data Augmentation for Meta-Learning
- Dynamic Scale Training for Object Detection
- Overton: A Data System for Monitoring and Improving Machine-Learned Products
- Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale
- SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labeling
- Regularizing Deep Networks with Semantic Data Augmentation
- Meta-Learning Symmetries by Reparameterization
- Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective
- Fixing the train-test resolution discrepancy
- XNAS: Neural Architecture Search with Expert Advice
- An Effective Anti-Aliasing Approach for Residual Networks
- Viewmaker Networks: Learning Views for Unsupervised Representation Learning
- Neural Transformation Learning for Deep Anomaly Detection Beyond Images
- Data Augmentation for Electrocardiogram Classification with Deep Neural Network
- Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data
- CIFAR-10 Image Classification Using Feature Ensembles
- Semi-Supervised Visual Representation Learning for Fashion Compatibility
- HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning
- Role-Wise Data Augmentation for Knowledge Distillation
- SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle
- MANAS: Multi-Agent Neural Architecture Search
- Neural Architecture Generator Optimization
- HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
- On the effectiveness of adversarial training against common corruptions
- Phase Transitions for the Information Bottleneck in Representation Learning
- MoViNets: Mobile Video Networks for Efficient Video Recognition
- AdaBits: Neural Network Quantization with Adaptive Bit-Widths
- Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models
- On Data-Augmentation and Consistency-Based Semi-Supervised Learning
- BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning
- Evolutionary-Neural Hybrid Agents for Architecture Search
- A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes
- EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations
- What do AI algorithms actually learn? - On false structures in deep learning
- MixPath: A Unified Approach for One-shot Neural Architecture Search
- Efficient Differentiable Neural Architecture Search with Meta Kernels
- LibFewShot: A Comprehensive Library for Few-shot Learning
- KeepAugment: A Simple Information-Preserving Data Augmentation Approach
- Using learned optimizers to make models robust to input noise
- Novelty Detection Via Blurring
- Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
- Data Augmentation for Deep Learning-based Radio Modulation Classification
- BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search
- Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
- Improving 3D Object Detection through Progressive Population Based Augmentation
- Inspector Gadget: A Data Programming-based Labeling System for Industrial Images
- On the Generalization Effects of Linear Transformations in Data Augmentation
- SGAS: Sequential Greedy Architecture Search
- Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness
- AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
- Neuroevolution of Neural Network Architectures Using CoDeepNEAT and Keras
- Strategy to Increase the Safety of a DNN-based Perception for HAD Systems
- Learning Optimal Conformal Classifiers
- Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
- Robust Nucleus Detection with Partially Labeled Exemplars
- VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
- Self-supervised Neural Architecture Search
- Neural Architecture Design for GPU-Efficient Networks
- Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining
- Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation
- Discrete Representations Strengthen Vision Transformer Robustness
- Efficient Neural Architecture Search via Proximal Iterations
- ALBA : Reinforcement Learning for Video Object Segmentation
- It Takes Two to Tango: Mixup for Deep Metric Learning
- FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
- Few-shot Neural Architecture Search
- Hierarchical Neural Architecture Search via Operator Clustering
- SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials
- Online Hyper-parameter Learning for Auto-Augmentation Strategy
- Improving Neural Architecture Search Image Classifiers via Ensemble Learning
- Adversarial Feature Augmentation and Normalization for Visual Recognition
- Data Augmentation for Object Detection via Differentiable Neural Rendering
- DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture
- Bit Error Robustness for Energy-Efficient DNN Accelerators
- Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training
- TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search
- Automated Learning Rate Scheduler for Large-batch Training
- Causally motivated Shortcut Removal Using Auxiliary Labels
- Escaping Saddle Points Faster with Stochastic Momentum
- PV-NAS: Practical Neural Architecture Search for Video Recognition
- Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
- When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks
- Improved Adversarial Robustness via Logit Regularization Methods
- A Framework for Studying Reinforcement Learning and Sim-to-Real in Robot Soccer
- A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
- ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
- Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning
- Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID
- CoKe: Localized Contrastive Learning for Robust Keypoint Detection
- VEGA: Towards an End-to-End Configurable AutoML Pipeline
- Dialog State Tracking with Reinforced Data Augmentation
- Learning to Generate Synthetic Data via Compositing
- MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning
- Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting
- E-Stitchup: Data Augmentation for Pre-Trained Embeddings
- Meta Approach to Data Augmentation Optimization
- Machine learning with limited data
- 1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021
- Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images
- How can AI Automate End-to-End Data Science?
- No One Representation to Rule Them All: Overlapping Features of Training Methods
- A Preliminary Study on Data Augmentation of Deep Learning for Image Classification
- EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization
- AdaSGD: Bridging the gap between SGD and Adam
- Neural Packet Classification
- ObjectAug: Object-level Data Augmentation for Semantic Image Segmentation
- An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization
- Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
- AlphaNet: Improved Training of Supernets with Alpha-Divergence
- Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks
- An Empirical Study and Analysis on Open-Set Semi-Supervised Learning
- Inner-Imaging Networks: Put Lenses into Convolutional Structure
- Privacy-preserving Collaborative Learning with Automatic Transformation Search
- McKernel: A Library for Approximate Kernel Expansions in Log-linear Time
- Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation
- GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
- AutoFlow: Learning a Better Training Set for Optical Flow
- Improving Robustness using Generated Data
- Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model
- A Survey of Techniques All Classifiers Can Learn from Deep Networks: Models, Optimizations, and Regularization
- Imponderous Net for Facial Expression Recognition in the Wild
- AutoEG: Automated Experience Grafting for Off-Policy Deep Reinforcement Learning
- HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
- Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
- Effective Evaluation of Deep Active Learning on Image Classification Tasks
- A Robotic Approach towards Quantifying Epipelagic Bound Plastic Using Deep Visual Models
- Defending Against Image Corruptions Through Adversarial Augmentations
- Learning Visual Representations for Transfer Learning by Suppressing Texture
- Learning from Data-Rich Problems: A Case Study on Genetic Variant Calling
- Stronger Baseline for Person Re-Identification
- Automatic Data Augmentation by Learning the Deterministic Policy
- A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels
- SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search
- Data augmentation and image understanding
- Random Shadows and Highlights: A new data augmentation method for extreme lighting conditions
- Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach
- Efficient Neural Architecture Search with Performance Prediction
- Selective sampling for accelerating training of deep neural networks
- On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective
- Regularized Evolutionary Population-Based Training
- Rethinking ResNets: Improved Stacking Strategies With High Order Schemes
- Pretraining Image Encoders without Reconstruction via Feature Prediction Loss
- Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
- Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks
- Margin-Based Regularization and Selective Sampling in Deep Neural Networks
- Patch augmentation: Towards efficient decision boundaries for neural networks
- BERT for Large-scale Video Segment Classification with Test-time Augmentation
- Deep Neural Network Ensembles
- Interpret-able feedback for AutoML systems
- Automatically Learning Data Augmentation Policies for Dialogue Tasks
- Exploiting Cross-Modal Prediction and Relation Consistency for Semi-Supervised Image Captioning
- Reweighting Augmented Samples by Minimizing the Maximal Expected Loss
- Learning image quality assessment by reinforcing task amenable data selection
- Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency
- Object-Aware Cropping for Self-Supervised Learning
- HERO: Hessian-Enhanced Robust Optimization for Unifying and Improving Generalization and Quantization Performance
- What augmentations are sensitive to hyper-parameters and why?
- Confounder Identification-free Causal Visual Feature Learning
- ExCon: Explanation-driven Supervised Contrastive Learning for Image Classification
- Robust Training Using Natural Transformation
- DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking
- Local Patch AutoAugment with Multi-Agent Collaboration
- Learning Purified Feature Representations from Task-irrelevant Labels
- Ferrograph image classification
- Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications
- Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks
- LogAvgExp Provides a Principled and Performant Global Pooling Operator
- Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data
- Reliable Label Bootstrapping for Semi-Supervised Learning
- Gradient-based Data Augmentation for Semi-Supervised Learning
- Efficient Model Performance Estimation via Feature Histories
- Similarity Transfer for Knowledge Distillation
- UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning
- Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training
- PanDA: Panoptic Data Augmentation
- Learning Non-Parametric Invariances from Data with Permanent Random Connectomes
- Hyperparameter Optimization in Neural Networks via Structured Sparse Recovery
- A Technical Report for VIPriors Image Classification Challenge
- On the Accuracy of CRNNs for Line-Based OCR: A Multi-Parameter Evaluation
- Dynamic Mode Decomposition based feature for Image Classification
- Exploring Frequency Domain Interpretation of Convolutional Neural Networks
- Dynamic Routing Networks
- EENA: Efficient Evolution of Neural Architecture
- ADWPNAS: Architecture-Driven Weight Prediction for Neural Architecture Search
- Differentiable Network Adaption with Elastic Search Space
- Exploiting Class Similarity for Machine Learning with Confidence Labels and Projective Loss Functions
- Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
- Deep Epidemiological Modeling by Black-box Knowledge Distillation: An Accurate Deep Learning Model for COVID-19
- Semi-supervised Learning of Fetal Anatomy from Ultrasound
- Unchain the Search Space with Hierarchical Differentiable Architecture Search
- Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation
- Efficient data augmentation using graph imputation neural networks
- Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning
- Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation
- Safe Augmentation: Learning Task-Specific Transformations from Data
- Communication-Efficient Separable Neural Network for Distributed Inference on Edge Devices
- Mixed precision in Graphics Processing Unit
- Revisiting Self-Training for Few-Shot Learning of Language Model
- Hierarchical Auxiliary Learning
- Exploring and Improving Mobile Level Vision Transformers
- Large-Scale Multi-Agent Deep FBSDEs
- DIVA: Dataset Derivative of a Learning Task
- EffCNet: An Efficient CondenseNet for Image Classification on NXP BlueBox
- Towards All-around Knowledge Transferring: Learning From Task-irrelevant Labels
- Geometric Data Augmentation Based on Feature Map Ensemble
- Doctor of Crosswise: Reducing Over-parametrization in Neural Networks
- A Reinforcement Learning Approach for Sequential Spatial Transformer Networks
- Understanding Modern Techniques in Optimization: Frank-Wolfe, Nesterov's Momentum, and Polyak's Momentum
- Inspect Transfer Learning Architecture with Dilated Convolution
- MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning
- Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions
- One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking
- Go Small and Similar: A Simple Output Decay Brings Better Performance
- A Generalization Theory based on Independent and Task-Identically Distributed Assumption
- FlipReID: Closing the Gap between Training and Inference in Person Re-Identification
- Signed Input Regularization
- What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance
- Sparsity-Probe: Analysis tool for Deep Learning Models
- ISyNet: Convolutional Neural Networks design for AI accelerator
- Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions
- Stochastic Contrastive Learning
- On the potential for open-endedness in neural networks
- FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection
- Robust Learning with Frequency Domain Regularization
- CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training Budgets
- Boosting Network Weight Separability via Feed-Backward Reconstruction
- Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
- Mining Domain Knowledge: Improved Framework towards Automatically Standardizing Anatomical Structure Nomenclature in Radiotherapy
- Contrastive Representation Learning with Trainable Augmentation Channel
- Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
- Implicit Label Augmentation on Partially Annotated Clips via Temporally-Adaptive Features Learning
- Research on Optimization Method of Multi-scale Fish Target Fast Detection Network