Related papers: On Pre-Trained Image Features and Synthetic Images…
Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide…
The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization…
In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one…
While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and…
A major challenges of deep learning (DL) is the necessity to collect huge amounts of training data. Often, the lack of a sufficiently large dataset discourages the use of DL in certain applications. Typically, acquiring the required amounts…
Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…
We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images. The proposed approach has three key ingredients: (1) 3D…
Deep Learning systems have proven to be extremely successful for image recognition tasks for which significant amounts of training data is available, e.g., on the famous ImageNet dataset. We demonstrate that for robotics applications with…
Deep learning methods have typically been trained on large datasets in which many training examples are available. However, many real-world product datasets have only a small number of images available for each product. We explore the use…
Crowdsourced 3D CAD models are becoming easily accessible online, and can potentially generate an infinite number of training images for almost any object category.We show that augmenting the training data of contemporary Deep Convolutional…
Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires…
Object detection has compelling applications over a range of domains, including human-computer interfaces, security and video surveillance, navigation and road traffic monitoring, transportation systems, industrial automation healthcare,…
In the fast-evolving field of artificial intelligence, where models are increasingly growing in complexity and size, the availability of labeled data for training deep learning models has become a significant challenge. Addressing complex…
Image forgery is a topic that has been studied for many years. Before the breakthrough of deep learning, forged images were detected using handcrafted features that did not require training. These traditional methods failed to perform…
A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature backbone is typically initialized with Imagenet classifier…
Traditionally, an object detector is applied to every part of the scene of interest, and its accuracy and computational cost increases with higher resolution images. However, in some application domains such as remote sensing, purchasing…
Computer vision algorithms with pixel-wise labeling tasks, such as semantic segmentation and salient object detection, have gone through a significant accuracy increase with the incorporation of deep learning. Deep segmentation methods…
The performance of a trained object detection neural network depends a lot on the image quality. Generally, images are pre-processed before feeding them into the neural network and domain knowledge about the image dataset is used to choose…
Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial networks (GANs). Recently, GANs are utilized as the training sample generator when obtaining or storing real training data is expensive…
To train well-performing generalizing neural networks, sufficiently large and diverse datasets are needed. Collecting data while adhering to privacy legislation becomes increasingly difficult and annotating these large datasets is both a…