Context Augmentation for Convolutional Neural Networks
Recent enhancements of deep convolutional neural networks (ConvNets) empowered by enormous amounts of labeled data have closed the gap with human performance for many object recognition tasks. These impressive results have generated interest in understanding and visualization of ConvNets. In this work, we study the effect of background in the task of image classification. Our results show that changing the backgrounds of the training datasets can have drastic effects on testing accuracies. Furthermore, we enhance existing augmentation techniques with the foreground segmented objects. The findings of this work are important in increasing the accuracies when only a small dataset is available, in creating datasets, and creating synthetic images.
Code (0)
등록된 구현이 없습니다.
Tasks
General Classificationimage-classificationImage ClassificationObject RecognitionSimilar Papers 제목 키워드 기반
Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations
We propose a novel data augmentation for labeled sentences called contextual augmentation. We assume an invariance that sentences are natural even if the words in the sentences are replaced with other words with paradigm…
Data AugmentationGeneral ClassificationLanguage ModelingLanguage Modelling+3Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms
In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network engineering and classification tasks. The …
Binary ClassificationData AugmentationDescriptiveGeneral ClassificationConditional BERT Contextual Augmentation
We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neu…
Data AugmentationLanguage ModelingLanguage ModellingText ClassificationImage Captioning using Deep Stacked LSTMs, Contextual Word Embeddings and Data Augmentation
Image Captioning, or the automatic generation of descriptions for images, is one of the core problems in Computer Vision and has seen considerable progress using Deep Learning Techniques. We propose to use Inception-ResN…
Data AugmentationDecoderImage CaptioningWord EmbeddingsAccuracy Improvement for Fully Convolutional Networks via Selective Augmentation with Applications to Electrocardiogram Data
Deep learning methods have shown suitability for time series classification in the health and medical domain, with promising results for electrocardiogram data classification. Successful identification of myocardial infa…
Data AugmentationGeneral ClassificationTime SeriesTime Series Analysis+1