Related papers: Learning to Edit Visual Programs with Self-Supervi…

Recent image inpainting methods have shown promising results due to the power of deep learning, which can explore external information available from the large training dataset. However, many state-of-the-art inpainting networks are still…

Recent image inpainting methods show promising results due to the power of deep learning, which can explore external information available from a large training dataset. However, many state-of-the-art inpainting networks are still limited…

The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been…

We investigate the potential of self-supervision in improving the accuracy of deep learning models trained to classify melanoma patches. Various self-supervision techniques such as rotation prediction, missing patch prediction, and…

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Recent advances have spurred incredible progress in self-supervised pretraining for vision. We investigate what factors may play a role in the utility of these pretraining methods for practitioners. To do this, we evaluate various…

There have been multiple recent proposals on using deep neural networks for code search using natural language. Common across these proposals is the idea of $\mathit{embedding}$ code and natural language queries, into real vectors and then…

We propose an interactive editing method that allows humans to help deep neural networks (DNNs) learn a latent space more consistent with human knowledge, thereby improving classification accuracy on indistinguishable ambiguous data.…

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any…

We introduce a novel self-supervised learning method based on adversarial training. Our objective is to train a discriminator network to distinguish real images from images with synthetic artifacts, and then to extract features from its…

This work presents the task of modifying images in an image editing program using natural language written commands. We utilize a corpus of over 6000 image edit text requests to alter real world images collected via crowdsourcing. A novel…

One-shot learning is usually tackled by using generative models or discriminative embeddings. Discriminative methods based on deep learning, which are very effective in other learning scenarios, are ill-suited for one-shot learning as they…

Over the years, computer vision researchers have spent an immense amount of effort on designing image features for the visual object recognition task. We propose to incorporate this valuable experience to guide the task of training deep…

We consider the task of one-shot learning of visual categories. In this paper we explore a Bayesian procedure for updating a pretrained convnet to classify a novel image category for which data is limited. We decompose this convnet into a…

Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both…

These days deep neural networks are ubiquitously used in a wide range of tasks, from image classification and machine translation to face identification and self-driving cars. In many applications, a single model error can lead to…

We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image. During training, our network gets the learning signal from a silhouette of an object in the input image - a form of…

Recently, large pretrained models (e.g., BERT, StyleGAN, CLIP) have shown great knowledge transfer and generalization capability on various downstream tasks within their domains. Inspired by these efforts, in this paper we propose a unified…