Related papers: Improving Learning Effectiveness For Object Detect…

Deep learning systems are optimized for clusters with homogeneous resources. However, heterogeneity is prevalent in computing infrastructure across edge, cloud and HPC. When training neural networks using stochastic gradient descent…

Deep Metric Learning trains a neural network to map input images to a lower-dimensional embedding space such that similar images are closer together than dissimilar images. When used for item retrieval, a query image is embedded using the…

Motion blur, out of focus, insufficient spatial resolution, lossy compression and many other factors can all cause an image to have poor quality. However, image quality is a largely ignored issue in traditional pattern recognition…

Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or fine-tune…

Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform…

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the…

We carefully evaluate a number of algorithms for learning in a federated environment, and test their utility for a variety of image classification tasks. We consider many issues that have not been adequately considered before: whether…

Visual quality inspection in high performance manufacturing can benefit from automation, due to cost savings and improved rigor. Deep learning techniques are the current state of the art for generic computer vision tasks like classification…

The robustness of object detection algorithms plays a prominent role in real-world applications, especially in uncontrolled environments due to distortions during image acquisition. It has been proven that the performance of object…

This paper investigates the impact of sampling and pretraining using datasets with different image characteristics on the performance of self-supervised learning (SSL) models for object classification. To do this, we sample two apartment…

Deep neural networks represent the gold standard for image classification. However, they usually need large amounts of data to reach superior performance. In this work, we focus on image classification problems with a few labeled examples…

In this paper, we present a semi supervised deep quick learning framework for instance detection and pixel-wise semantic segmentation of images in a dense clutter of items. The framework can quickly and incrementally learn novel items in an…

For safety-critical applications such as autonomous driving, CNNs have to be robust with respect to unavoidable image corruptions, such as image noise. While previous works addressed the task of robust prediction in the context of…

Recent years have witnessed the remarkable developments made by deep learning techniques for object detection, a fundamentally challenging problem of computer vision. Nevertheless, there are still difficulties in training accurate deep…

The wide and rapid adoption of deep learning by practitioners brought unintended consequences in many situations such as in the infamous case of Google Photos' racist image recognition algorithm; thus, necessitated the utilization of the…

Feature disentanglement of the foreground target objects and the background surrounding context has not been yet fully accomplished. The lack of network interpretability prevents advancing for feature disentanglement and better…

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…

Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with…

Active learning is an important technology for automated machine learning systems. In contrast to Neural Architecture Search (NAS) which aims at automating neural network architecture design, active learning aims at automating training data…

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…