Related papers: Exploring Unlabeled Faces for Novel Attribute Disc…
Person re-identification aims to match a person's identity across multiple camera streams. Deep neural networks have been successfully applied to the challenging person re-identification task. One remarkable bottleneck is that the existing…
State-of-the-art face recognition systems require vast amounts of labeled training data. Given the priority of privacy in face recognition applications, the data is limited to celebrity web crawls, which have issues such as limited numbers…
By utilizing label distribution learning, a probability distribution is assigned for a facial image to express a compound emotion, which effectively improves the problem of label uncertainties and noises occurred in one-hot labels. In…
In this paper, we tackle the problem of novel visual category discovery, i.e., grouping unlabelled images from new classes into different semantic partitions by leveraging a labelled dataset that contains images from other different but…
Great labels make great models. However, traditional labeling approaches for tasks like object detection have substantial costs at scale. Furthermore, alternatives to fully-supervised object detection either lose functionality or require…
Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…
The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…
Unsupervised image-to-image translation methods aim to map images from one domain into plausible examples from another domain while preserving structures shared across two domains. In the many-to-many setting, an additional guidance example…
Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…
Given labeled data in a source domain, unsupervised domain adaptation has been widely adopted to generalize models for unlabeled data in a target domain, whose data distributions are different. However, existing works are inapplicable to…
Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…
Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a "learning via translation" framework. In the baseline, we translate the labeled images from source to…
Image to image translation is the problem of transferring an image from a source domain to a different (but related) target domain. We present a new unsupervised image to image translation technique that leverages the underlying semantic…
It's useful to automatically transform an image from its original form to some synthetic form (style, partial contents, etc.), while keeping the original structure or semantics. We define this requirement as the "image-to-image translation"…
The growing scale of face recognition datasets empowers us to train strong convolutional networks for face recognition. While a variety of architectures and loss functions have been devised, we still have a limited understanding of the…
As a significant step for human face modeling, editing, and generation, face landmarking aims at extracting facial keypoints from images. A generalizable face landmarker is required in practice because real-world facial images, e.g., the…
Semi-supervised medical image segmentation has gained growing interest due to its ability to utilize unannotated data. The current state-of-the-art methods mostly rely on pseudo-labeling within a co-training framework. These methods depend…
Deep learning has raised hopes and expectations as a general solution for many applications; indeed it has proven effective, but it also showed a strong dependence on large quantities of data. Luckily, it has been shown that, even when data…
This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses…
To learn semantic attributes, existing methods typically train one discriminative model for each word in a vocabulary of nameable properties. However, this "one model per word" assumption is problematic: while a word might have a precise…