Related papers: Addressing Challenging Place Recognition Tasks usi…
In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial networks (GANs) can be used for multiple purposes. Triple-GAN,…
As synthetic imagery is used more frequently in training deep models, it is important to understand how different synthesis techniques impact the performance of such models. In this work, we perform a thorough evaluation of the…
Adverse weather image translation belongs to the unsupervised image-to-image (I2I) translation task which aims to transfer adverse condition domain (eg, rainy night) to standard domain (eg, day). It is a challenging task because images from…
Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all…
Although deep convolutional networks have achieved great performance in face recognition tasks, the challenge of domain discrepancy still exists in real world applications. Lack of domain coverage of training data (source domain) makes the…
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training…
Deep learning techniques, especially Generative Adversarial Networks (GANs) have significantly improved image inpainting and image-to-image translation tasks over the past few years. To the best of our knowledge, the problem of combining…
Generative Adversarial Networks (GANs) are a well-known technique that is trained on samples (e.g. pictures of fruits) and which after training is able to generate realistic new samples. Conditional GANs (CGANs) additionally provide label…
The superior performance introduced by deep learning approaches in removing atmospheric particles such as snow and rain from a single image; favors their usage over classical ones. However, deep learning-based approaches still suffer from…
Unsupervised image-to-image translation consists of learning a pair of mappings between two domains without known pairwise correspondences between points. The current convention is to approach this task with cycle-consistent GANs: using a…
Acquisition of data in task-specific applications of machine learning like plant disease recognition is a costly endeavor owing to the requirements of professional human diligence and time constraints. In this paper, we present a simple…
For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and…
Place recognition is a cornerstone of vehicle navigation and mapping, which is pivotal in enabling systems to determine whether a location has been previously visited. This capability is critical for tasks such as loop closure in…
In this paper, we propose Factorized Adversarial Networks (FAN) to solve unsupervised domain adaptation problems for image classification tasks. Our networks map the data distribution into a latent feature space, which is factorized into a…
Generative adversarial networks (GANs) have shown significant potential in modeling high dimensional distributions of image data, especially on image-to-image translation tasks. However, due to the complexity of these tasks,…
Image-to-image (i2i) networks struggle to capture local changes because they do not affect the global scene structure. For example, translating from highway scenes to offroad, i2i networks easily focus on global color features but ignore…
In classification tasks, the classification accuracy diminishes when the data is gathered in different domains. To address this problem, in this paper, we investigate several adversarial models for domain adaptation (DA) and their effect on…
Image translation is a burgeoning field in computer vision where the goal is to learn the mapping between an input image and an output image. However, most recent methods require multiple generators for modeling different domain mappings,…
The goal of this work is to improve images of traffic scenes that are degraded by natural causes such as fog, rain and limited visibility during the night. For these applications, it is next to impossible to get pixel perfect pairs of the…
The Generative Models have gained considerable attention in the field of unsupervised learning via a new and practical framework called Generative Adversarial Networks (GAN) due to its outstanding data generation capability. Many models of…