Related papers: Stylized Structural Patterns for Improved Neural N…

Deep learning approaches have become the standard solution to many problems in computer vision and robotics, but obtaining sufficient training data in high enough quality is challenging, as human labor is error prone, time consuming, and…

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a result, the research challenge shifts from devising…

Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains non-trivial. Not only is the number of possible comparisons quadratic in the number of training images, but also access to images…

We propose a simple and efficient method for exploiting synthetic images when training a Deep Network to predict a 3D pose from an image. The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy…

Foundation models in digital pathology use massive datasets to learn useful compact feature representations of complex histology images. However, there is limited transparency into what drives the correlation between dataset size and…

A major challenges of deep learning (DL) is the necessity to collect huge amounts of training data. Often, the lack of a sufficiently large dataset discourages the use of DL in certain applications. Typically, acquiring the required amounts…

Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets.…

Deep image prior (DIP) was recently introduced as an effective unsupervised approach for image restoration tasks. DIP represents the image to be recovered as the output of a deep convolutional neural network, and learns the network's…

Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing the occurrence of occlusions or varying environmental and…

We introduce SynthLight, a diffusion model for portrait relighting. Our approach frames image relighting as a re-rendering problem, where pixels are transformed in response to changes in environmental lighting conditions. Using a…

Precise semantic segmentation of crops and weeds is necessary for agricultural weeding robots. However, training deep learning models requires large annotated datasets, which are costly to obtain in real fields. Synthetic data can reduce…

The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem…

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…

Although learning-based image restoration methods have made significant progress, they still struggle with limited generalization to real-world scenarios due to the substantial domain gap caused by training on synthetic data. Existing…

The strength of machine learning models stems from their ability to learn complex function approximations from data; however, this strength also makes training deep neural networks challenging. Notably, the complex models tend to memorize…

Makeup transfer aims to apply the makeup style of a reference portrait to a source portrait while preserving identity and background. Early methods formulate this task as unsupervised image-to-image translation, relying on surrogate…

Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…

Formula-driven supervised learning (FDSL) has been shown to be an effective method for pre-training vision transformers, where ExFractalDB-21k was shown to exceed the pre-training effect of ImageNet-21k. These studies also indicate that…

New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and…