Related papers: How many labeled license plates are needed?
Data augmentation is a critical contributing factor to the success of deep learning but heavily relies on prior domain knowledge which is not always available. Recent works on automatic data augmentation learn a policy to form a sequence of…
Augmenting data in image space (eg. flipping, cropping etc) and activation space (eg. dropout) are being widely used to regularise deep neural networks and have been successfully applied on several computer vision tasks. Unlike previous…
Annotating images with pixel-wise labels is a time-consuming and costly process. Recently, DatasetGAN showcased a promising alternative - to synthesize a large labeled dataset via a generative adversarial network (GAN) by exploiting a small…
Mobile robots and autonomous vehicles rely on multi-modal sensor setups to perceive and understand their surroundings. Aside from cameras, LiDAR sensors represent a central component of state-of-the-art perception systems. In addition to…
Data augmentations are useful in closing the sim-to-real domain gap when training on synthetic data. This is because they widen the training data distribution, thus encouraging the model to generalize better to other domains. Many image…
Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear…
In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label…
Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…
Generative Adversarial Networks (GANs) have been used widely to generate large volumes of synthetic data. This data is being utilized for augmenting with real examples in order to train deep Convolutional Neural Networks (CNNs). Studies…
Data seems cheap to get, and in many ways it is, but the process of creating a high quality labeled dataset from a mass of data is time-consuming and expensive. With the advent of rich 3D repositories, photo-realistic rendering systems…
Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…
Convolutional Neural Network (CNN)-based accurate prediction typically requires large-scale annotated training data. In Medical Imaging, however, both obtaining medical data and annotating them by expert physicians are challenging; to…
Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…
Deep neural network models have recently achieved state-of-the-art performance gains in a variety of natural language processing (NLP) tasks (Young, Hazarika, Poria, & Cambria, 2017). However, these gains rely on the availability of large…
Understanding a surgical scene is crucial for computer-assisted surgery systems to provide any intelligent assistance functionality. One way of achieving this scene understanding is via scene segmentation, where every pixel of a frame is…
When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In…
In recent years, deep neural networks (DNNs) have gained remarkable achievement in computer vision tasks, and the success of DNNs often depends greatly on the richness of data. However, the acquisition process of data and high-quality…
With the development of deep learning, Neural Network is commonly adopted to the License Plate Detection (LPD) task and achieves much better performance and precision, especially CNN-based networks can achieve state of the art RetinaNet[1].…
Most design methods contain a forward framework, asking for primary specifications of a building to generate an output or assess its performance. However, architects urge for specific objectives though uncertain of the proper design…
Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training. Most existing work focuses on constructing a unified policy applicable to…