Image Augmentation
100 papers with code • 1 benchmarks • 1 datasets
Image Augmentation is a data augmentation method that generates more training data from the existing training samples. Image Augmentation is especially useful in domains where training data is limited or expensive to obtain like in biomedical applications.
Source: Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing
( Image credit: Kornia )
Libraries
Use these libraries to find Image Augmentation models and implementationsLatest papers
Zero-Shot Learning by Harnessing Adversarial Samples
To take the advantage of image augmentations while mitigating the semantic distortion issue, we propose a novel ZSL approach by Harnessing Adversarial Samples (HAS).
Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation
As such, we explore how natural language descriptions of the domains seen in training data can be used with large vision models trained on diverse pretraining datasets to generate useful variations of the training data.
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model.
Performance of GAN-based augmentation for deep learning COVID-19 image classification
Data augmentation is a typical methodology used in machine learning when confronted with a limited data set.
CamDiff: Camouflage Image Augmentation via Diffusion Model
Specifically, we leverage the latent diffusion model to synthesize salient objects in camouflaged scenes, while using the zero-shot image classification ability of the Contrastive Language-Image Pre-training (CLIP) model to prevent synthesis failures and ensure the synthesized object aligns with the input prompt.
Improving the Transferability of Adversarial Samples by Path-Augmented Method
However, such methods selected the image augmentation path heuristically and may augment images that are semantics-inconsistent with the target images, which harms the transferability of the generated adversarial samples.
BioImageLoader: Easy Handling of Bioimage Datasets for Machine Learning
BioImageLoader (BIL) is a python library that handles bioimage datasets for machine learning applications, easing simple workflows and enabling complex ones.
Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning
They have overlooked the wide characteristic changes of different classes and can not model abundant intra-class variations for generations.
Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
Large-scale vision-language pre-trained (VLP) models are prone to hallucinate non-existent visual objects when generating text based on visual information.
Self-adversarial Multi-scale Contrastive Learning for Semantic Segmentation of Thermal Facial Images
Limited availability of datasets from unconstrained settings further limits the use of the state-of-the-art segmentation networks, loss functions and learning strategies which have been built and validated for RGB images.