Related papers: Improved Image Augmentation for Convolutional Neur…
Image copy detection and retrieval from large databases leverage two components. First, a neural network maps an image to a vector representation, that is relatively robust to various transformations of the image. Second, an efficient but…
Seam carving is a representative content-aware image retargeting approach to adjust the size of an image while preserving its visually prominent content. To maintain visually important content, seam-carving algorithms first calculate the…
What can neural networks learn about the visual world when provided with only a single image as input? While any image obviously cannot contain the multitudes of all existing objects, scenes and lighting conditions - within the space of all…
Increasing spatial image resolution is an often required, yet challenging task in image acquisition. Recently, it has been shown that it is possible to obtain a high resolution image by covering a low resolution sensor with a non-regular…
Using a large number of parameters , deep neural networks have achieved remarkable performance on computer vison and natural language processing tasks. However the networks usually suffer from overfitting by using too much parameters.…
Stain variation is a phenomenon observed when distinct pathology laboratories stain tissue slides that exhibit similar but not identical color appearance. Due to this color shift between laboratories, convolutional neural networks (CNNs)…
A recurring problem faced when training neural networks is that there is typically not enough data to maximize the generalization capability of deep neural networks(DNN). There are many techniques to address this, including data…
In this paper we report on improved part segmentation performance using convolutional neural networks to reduce the dependency on the large amount of manually annotated empirical images. This was achieved by optimising the visual realism of…
Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have…
In the last decade, Convolutional Neural Network (CNN) and transformer based object detectors have achieved high performance on a large variety of datasets. Though the majority of detection literature has developed this capability on…
Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for…
Text-to-image generation requires large amount of training data to synthesizing high-quality images. For augmenting training data, previous methods rely on data interpolations like cropping, flipping, and mixing up, which fail to introduce…
Copy detection, which is a task to determine whether an image is a modified copy of any image in a database, is an unsolved problem. Thus, we addressed copy detection by training convolutional neural networks (CNNs) with contrastive…
Regularization in convolutional neural networks (CNNs) is usually addressed with dropout layers. However, dropout is sometimes detrimental in the convolutional part of a CNN as it simply sets to zero a percentage of pixels in the feature…
It is difficult to collect data on a large scale in a monocular depth estimation because the task requires the simultaneous acquisition of RGB images and depths. Data augmentation is thus important to this task. However, there has been…
Brain lesion segmentation provides a valuable tool for clinical diagnosis, and convolutional neural networks (CNNs) have achieved unprecedented success in the task. Data augmentation is a widely used strategy that improves the training of…
Neural networks are capable of learning powerful representations of data, but they are susceptible to overfitting due to the number of parameters. This is particularly challenging in the domain of time series classification, where datasets…
For proper generalization performance of convolutional neural networks (CNNs) in medical image segmentation, the learnt features should be invariant under particular non-linear shape variations of the input. To induce invariance in CNNs to…
We present You Only Cut Once (YOCO) for performing data augmentations. YOCO cuts one image into two pieces and performs data augmentations individually within each piece. Applying YOCO improves the diversity of the augmentation per sample…
State-of-the-art visual under-canopy navigation methods are designed with deep learning-based perception models to distinguish traversable space from crop rows. While these models have demonstrated successful performance, they require large…