Related papers: Self-Supervised One-Shot Learning for Automatic Se…
Deep learning-based approaches achieve state-of-the-art performance in the majority of image segmentation benchmarks. However, training of such models requires a sizable amount of manual annotations. In order to reduce this effort, we…
Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks. Different works have improved the limited understanding of the latent space of GANs by embedding images…
Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in…
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…
Zero-shot learning (ZSL) is commonly used to address the very pervasive problem of predicting unseen classes in fine-grained image classification and other tasks. One family of solutions is to learn synthesised unseen visual samples…
Joint synthesis of images and segmentation masks with generative adversarial networks (GANs) is promising to reduce the effort needed for collecting image data with pixel-wise annotations. However, to learn high-fidelity image-mask…
Low-shot learning methods for image classification support learning from sparse data. We extend these techniques to support dense semantic image segmentation. Specifically, we train a network that, given a small set of annotated images,…
While GANs have shown success in realistic image generation, the idea of using GANs for other tasks unrelated to synthesis is underexplored. Do GANs learn meaningful structural parts of objects during their attempt to reproduce those…
We present a novel approach to image manipulation and understanding by simultaneously learning to segment object masks, paste objects to another background image, and remove them from original images. For this purpose, we develop a novel…
A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple…
We introduce EnhanceGAN, an adversarial learning based model that performs automatic image enhancement. Traditional image enhancement frameworks typically involve training models in a fully-supervised manner, which require expensive…
Image inpainting techniques have shown promising improvement with the assistance of generative adversarial networks (GANs) recently. However, most of them often suffered from completed results with unreasonable structure or blurriness. To…
One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes. To alleviate this problem, off-the-shelf image generation techniques based on Generative Adversarial…
The latent code of the recent popular model StyleGAN has learned disentangled representations thanks to the multi-layer style-based generator. Embedding a given image back to the latent space of StyleGAN enables wide interesting semantic…
As deep learning methods continue to improve medical image segmentation performance, data annotation is still a big bottleneck due to the labor-intensive and time-consuming burden on medical experts, especially for 3D images. To…
Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…
Fine-grained image classification involves identifying different subcategories of a class which possess very subtle discriminatory features. Fine-grained datasets usually provide bounding box annotations along with class labels to aid the…
Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly…
Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior ZSL approaches focus on improving the discriminant power of…
Due to the various reasons such as atmospheric effects and differences in acquisition, it is often the case that there exists a large difference between spectral bands of satellite images collected from different geographic locations. The…