相关论文: The Surprising Effectiveness of Linear Unsupervise…

The reconstruction of a high resolution image given a low resolution observation is an ill-posed inverse problem in imaging. Deep learning methods rely on training data to learn an end-to-end mapping from a low-resolution input to a…

We investigate the behavior of maps learned by machine translation methods. The maps translate words by projecting between word embedding spaces of different languages. We locally approximate these maps using linear maps, and find that they…

Recently image-to-image translation has attracted significant interests in the literature, starting from the successful use of the generative adversarial network (GAN), to the introduction of cyclic constraint, to extensions to multiple…

Deep neural networks often struggle to learn robust representations in the presence of dataset biases, leading to suboptimal generalization on unbiased datasets. This limitation arises because the models heavily depend on peripheral and…

Intrinsic image decomposition (IID) is the task that decomposes a natural image into albedo and shade. While IID is typically solved through supervised learning methods, it is not ideal due to the difficulty in observing ground truth albedo…

In this paper, we tackle the problem of enhancing real-world low-light images with significant noise in an unsupervised fashion. Conventional unsupervised learning-based approaches usually tackle the low-light image enhancement problem…

This work presents the first convolutional neural network that learns an image-to-graph translation task without needing external supervision. Obtaining graph representations of image content, where objects are represented as nodes and…

Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer…

Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition. But do unsupervised computer vision…

State-of-the-art deep neural network models have reached near perfect face recognition accuracy rates on controlled high-resolution face images. However, their performance is drastically degraded when they are tested with very…

Although deep learning are commonly employed for image recognition, usually huge amount of labeled training data is required, which may not always be readily available. This leads to a noticeable performance disparity when compared to…

Robust model fitting is a core algorithm in a large number of computer vision applications. Solving this problem efficiently for datasets highly contaminated with outliers is, however, still challenging due to the underlying computational…

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some…

Image-to-image translation is a general name for a task where an image from one domain is converted to a corresponding image in another domain, given sufficient training data. Traditionally different approaches have been proposed depending…

Unpaired image-to-image translation (UNIT) aims to map images between two visual domains without paired training data. However, given a UNIT model trained on certain domains, it is difficult for current methods to incorporate new domains…

Many applications, such as autonomous driving, heavily rely on multi-modal data where spatial alignment between the modalities is required. Most multi-modal registration methods struggle computing the spatial correspondence between the…

Unsupervised neural machine translation (UNMT) has recently achieved remarkable results with only large monolingual corpora in each language. However, the uncertainty of associating target with source sentences makes UNMT theoretically an…

Unsupervised image-to-image translation is an important and challenging problem in computer vision. Given an image in the source domain, the goal is to learn the conditional distribution of corresponding images in the target domain, without…