Browse SoTA > Methodology > Data Augmentation

Data Augmentation

376 papers with code ยท Methodology

( Image credit: Albumentations )

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Latest papers without code

A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks

30 Jul 2020

Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wrong classification results.

DATA AUGMENTATION

Learning from Few Samples: A Survey

30 Jul 2020

Deep neural networks have been able to outperform humans in some cases like image recognition and image classification.

DATA AUGMENTATION FEW-SHOT LEARNING IMAGE CLASSIFICATION OMNIGLOT

Reliable Tuberculosis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization

29 Jul 2020

The accuracy, precision, sensitivity, F1-score, specificity in the detection of tuberculosis using X-ray images were 97. 07 %, 97. 34 %, 97. 07 %, 97. 14 % and 97. 36 % respectively.

DATA AUGMENTATION SEMANTIC SEGMENTATION TRANSFER LEARNING

Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction

29 Jul 2020

In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels.

CONTRASTIVE LEARNING DATA AUGMENTATION

KOVIS: Keypoint-based Visual Servoing with Zero-Shot Sim-to-Real Transfer for Robotics Manipulation

28 Jul 2020

We train the deep neural network only in the simulated environment; and the trained model could be directly used for real-world visual servoing tasks.

DATA AUGMENTATION SELF-SUPERVISED LEARNING

Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing

27 Jul 2020

Our data analysis on facial attribute recognition demonstrates (1) the attribution of model bias from imbalanced training data distribution and (2) the potential of adversarial examples in balancing data distribution.

ADVERSARIAL ATTACK DATA AUGMENTATION FEW-SHOT LEARNING IMAGE CLASSIFICATION

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

27 Jul 2020

In this paper, we propose part-aware data augmentation (PA-AUG) that can better utilize rich information of 3D label to enhance the performance of 3D object detectors.

3D OBJECT DETECTION DATA AUGMENTATION

Representation Learning with Video Deep InfoMax

27 Jul 2020

DeepInfoMax (DIM) is a self-supervised method which leverages the internal structure of deep networks to construct such views, forming prediction tasks between local features which depend on small patches in an image and global features which depend on the whole image.

ACTION RECOGNITION DATA AUGMENTATION REPRESENTATION LEARNING SELF-SUPERVISED LEARNING

Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification

27 Jul 2020

We argue that for pair-wise matchers that rely on metric learning, e. g., Siamese networks for person ReID, the unsupervised domain adaptation (UDA) objective should consist in aligning pair-wise dissimilarity between domains, rather than aligning feature representations.

DATA AUGMENTATION METRIC LEARNING PERSON RE-IDENTIFICATION UNSUPERVISED DOMAIN ADAPTATION