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.
SOTA for Image Classification on SVHN
We provide examples of image augmentations for different computer vision tasks and show that Albumentations is faster than other commonly used image augmentation tools on the most of commonly used image transformations.
We demonstrate that by making subtle but important changes to the model architecture and the learning rate schedule, fine-tuning image features, and adding data augmentation, we can significantly improve the performance of the up-down model on VQA v2. 0 dataset -- from 65. 67% to 70. 22%.
#2 best model for Visual Question Answering on VQA v2
Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy.
#8 best model for Object Detection on PASCAL VOC 2007
In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively.
SOTA for Face Detection on FDDB
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
With LSR, we demonstrate consistent improvement in all systems regardless of the extent of over-fitting.
#14 best model for Person Re-Identification on Market-1501
There is large consent that successful training of deep networks requires many thousand annotated training samples.
NiftyNet provides a modular deep-learning pipeline for a range of medical imaging applications including segmentation, regression, image generation and representation learning applications.