Related papers: Automated Synthetic-to-Real Generalization

We consider the targeted image editing problem: blending a region in a source image with a driver image that specifies the desired change. Differently from prior works, we solve this problem by learning a conditional probability…

Synthesizing realistic medical images provides a feasible solution to the shortage of training data in deep learning based medical image recognition systems. However, the quality control of synthetic images for data augmentation purposes is…

Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or hard to annotate. Synthetic data generation, however, can itself be prohibitively…

The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language…

Unstructured urban environments present unique challenges for scene understanding and generalization due to their complex and diverse layouts. We introduce SynthGenNet, a self-supervised student-teacher architecture designed to enable…

Deep learning approaches heavily rely on high-quality human supervision which is nonetheless expensive, time-consuming, and error-prone, especially for image segmentation task. In this paper, we propose a method to automatically synthesize…

We develop a Learning Direct Optimization (LiDO) method for the refinement of a latent variable model that describes input image x. Our goal is to explain a single image x with an interpretable 3D computer graphics model having scene graph…

Exploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the…

The concept of sparsity has been extensively applied for regularization in image reconstruction. Typically, sparsifying transforms are either pre-trained on ground-truth images or adaptively trained during the reconstruction. Thereby,…

Current generative networks are increasingly proficient in generating high-resolution realistic images. These generative networks, especially the conditional ones, can potentially become a great tool for providing new image datasets. This…

Despite that the performance of image-to-image translation has been significantly improved by recent progress in generative models, current methods still suffer from severe degradation in training stability and sample quality when applied…

Text information including extensive prior knowledge about land cover classes has been ignored in hyperspectral image classification (HSI) tasks. It is necessary to explore the effectiveness of linguistic mode in assisting HSI…

The heightened realism of AI-generated images can be attributed to the rapid development of synthetic models, including generative adversarial networks (GANs) and diffusion models (DMs). The malevolent use of synthetic images, such as the…

How to design proper training pairs is critical for super-resolving real-world low-quality (LQ) images, which suffers from the difficulties in either acquiring paired ground-truth high-quality (HQ) images or synthesizing photo-realistic…

Active Learning (AL) represents a crucial methodology within machine learning, emphasizing the identification and utilization of the most informative samples for efficient model training. However, a significant challenge of AL is its…

Generative models are widely employed to enhance the photorealism of visual synthetic data for training computer vision algorithms. However, they often introduce visual artifacts that degrade the accuracy of these algorithms and require…

Data augmentations are useful in closing the sim-to-real domain gap when training on synthetic data. This is because they widen the training data distribution, thus encouraging the model to generalize better to other domains. Many image…

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a…

Some image restoration tasks like demosaicing require difficult training samples to learn effective models. Existing methods attempt to address this data training problem by manually collecting a new training dataset that contains adequate…

Synthetic data can improve generalization when real data is scarce, but excessive reliance may introduce distributional mismatches that degrade performance. In this paper, we present a learning-theoretic framework to quantify the trade-off…