Related papers: Guiding InfoGAN with Semi-Supervision
The success of deep learning for medical imaging tasks, such as classification, is heavily reliant on the availability of large-scale datasets. However, acquiring datasets with large quantities of labeled data is challenging, as labeling is…
Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…
In recent years, Generative Adversarial Networks (GAN) have emerged as a powerful method for learning the mapping from noisy latent spaces to realistic data samples in high-dimensional space. So far, the development and application of GANs…
Hashing has been a widely-adopted technique for nearest neighbor search in large-scale image retrieval tasks. Recent research has shown that leveraging supervised information can lead to high quality hashing. However, the cost of annotating…
In the last few years, unpaired image-to-image translation has witnessed remarkable progress. Although the latest methods are able to generate realistic images, they crucially rely on a large number of labeled images. Recently, some methods…
We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification…
In recent years, considerable advancements have been made in the area of Generative Adversarial Networks (GANs), particularly with the advent of style-based architectures that address many key shortcomings - both in terms of modeling…
As social media continues to grow rapidly, the prevalence of harassment on these platforms has also increased. This has piqued the interest of researchers in the field of fake detection. Social media data, often forms complex graphs with…
This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are…
Device-free wireless indoor localization is a key enabling technology for the Internet of Things (IoT). Fingerprint-based indoor localization techniques are a commonly used solution. This paper proposes a semi-supervised, generative…
Annotating images with pixel-wise labels is a time-consuming and costly process. Recently, DatasetGAN showcased a promising alternative - to synthesize a large labeled dataset via a generative adversarial network (GAN) by exploiting a small…
With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due…
Weakly-supervised learning has become a popular technology in recent years. In this paper, we propose a novel medical image classification algorithm, called Weakly-Supervised Generative Adversarial Networks (WSGAN), which only uses a small…
In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled…
Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…
We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality of synthesized images is far from satisfactory due to three…
In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotation efforts. Particularly, we propose a strategy that…
Data augmentation is rapidly gaining attention in machine learning. Synthetic data can be generated by simple transformations or through the data distribution. In the latter case, the main challenge is to estimate the label associated to…
Deep Learning for Computer Vision depends mainly on the source of supervision.Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance. We propose…