Related papers: Learning Functors using Gradient Descent

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

Graph Convolutional Networks (GCNs) are a class of general models that can learn from graph structured data. Despite being general, GCNs are admittedly inferior to convolutional neural networks (CNNs) when applied to vision tasks, mainly…

As an integral component of blind image deblurring, non-blind deconvolution removes image blur with a given blur kernel, which is essential but difficult due to the ill-posed nature of the inverse problem. The predominant approach is based…

Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of…

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, iterate trajectories, function value oscillations, and especially its implicit acceleration,…

We present a method for simultaneously learning, in an unsupervised manner, (i) a conditional image generator, (ii) foreground extraction and segmentation, (iii) clustering into a two-level class hierarchy, and (iv) object removal and…

The ability to flexibly bind features into coherent wholes from different perspectives is a hallmark of cognition and intelligence. Importantly, the binding problem is not only relevant for vision but also for general intelligence,…

Existing approaches for restoring weather-degraded images follow a fully-supervised paradigm and they require paired data for training. However, collecting paired data for weather degradations is extremely challenging, and existing methods…

We introduce a diffusion-based cross-domain image translator in the absence of paired training data. Unlike GAN-based methods, our approach integrates diffusion models to learn the image translation process, allowing for more coverable…

We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc. We start from an image autoencoder architecture with fixed weights. For each task we…

Cycle reconstruction regularized adversarial training -- e.g., CycleGAN, DiscoGAN, and DualGAN -- has been widely used for image style transfer with unpaired training data. Several recent works, however, have shown that local distortions…

Deep learning has gained great success in various classification tasks. Typically, deep learning models learn underlying features directly from data, and no underlying relationship between classes are included. Similarity between classes…

Medical image translation is an ill-posed problem. Unlike existing paired unbounded unidirectional translation networks, in this paper, we consider unpaired medical images and provide a strictly bounded network that yields a stable…

We describe an alternative learning method for neural networks, which we call Blind Descent. By design, Blind Descent does not face problems like exploding or vanishing gradients. In Blind Descent, gradients are not used to guide the…

Unpaired image-to-image translation is the problem of mapping an image in the source domain to one in the target domain, without requiring corresponding image pairs. To ensure the translated images are realistically plausible, recent works,…

Generative Adversarial Networks (GANs) are a powerful class of generative models. Despite their successes, the most appropriate choice of a GAN network architecture is still not well understood. GAN models for image synthesis have adopted a…

Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can…

Unpaired Image-to-Image translation aims to convert the image from one domain (input domain A) to another domain (target domain B), without providing paired examples for the training. The state-of-the-art, Cycle-GAN demonstrated the power…

Instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segment a new modality by either deploying a pre-trained model…