Related papers: Unsupervised learning on spontaneous retinal activ…

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such…

In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its…

Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form. Graphs can be used to model several scenarios, from molecules and materials to RNA secondary structures. Several…

Understanding how the visual cortex of the human brain really works is still an open problem for science today. A better understanding of natural intelligence could also benefit object-recognition algorithms based on convolutional neural…

Conventional supervised super-resolution (SR) approaches are trained with massive external SR datasets but fail to exploit desirable properties of the given test image. On the other hand, self-supervised SR approaches utilize the internal…

Over the brief time intervals available for processing retinal output, roughly 50 to 300 msec, the number of extra spikes generated by individual ganglion cells can be quite variable. Here, computer-generated spike trains were used to…

Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data…

We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-supervised and contrastive learning. We shed light on the…

Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase…

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn…

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be…

Self-supervised pre-training for 3D vision has drawn increasing research interest in recent years. In order to learn informative representations, a lot of previous works exploit invariances of 3D features, e.g., perspective-invariance…

In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale image classification…

The impact of convolution neural networks (CNNs) in the supervised settings provided tremendous increment in performance. The representations learned from CNN's operated on hyperspherical manifold led to insightful outcomes in face…

Recently, deep feedforward neural networks have achieved considerable success in modeling biological sensory processing, in terms of reproducing the input-output map of sensory neurons. However, such models raise profound questions about…

Deep convolutional neural networks (CNNs) have demonstrated impressive performance on visual object classification tasks. In addition, it is a useful model for predication of neuronal responses recorded in visual system. However, there is…

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based…

The ability to predict future states of the environment is a central pillar of intelligence. At its core, effective prediction requires an internal model of the world and an understanding of the rules by which the world changes. Here, we…

This work presents a novel method of exploring human brain-visual representations, with a view towards replicating these processes in machines. The core idea is to learn plausible computational and biological representations by correlating…

Fundus photography is the primary method for retinal imaging and essential for diabetic retinopathy prevention. Automated segmentation of fundus photographs would improve the quality, capacity, and cost-effectiveness of eye care screening…