Related papers: Benchmarking and Analyzing Generative Data for Vis…

This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e.g. visual attributes) while the others are defined by exemplar images as well. This task is often referred to…

Recent advancements in image generation models have enabled the prediction of future Graphical User Interface (GUI) states based on user instructions. However, existing benchmarks primarily focus on general domain visual fidelity, leaving…

Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is critical to test their behaviors in varied and complex scenes in…

Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often relying on narrow, task-specific datasets and inconsistent…

Classifiers and generators have long been separated. We break down this separation and showcase that conventional neural network classifiers can generate high-quality images of a large number of categories, being comparable to the…

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…

Most evaluations of generative models rely on feature-distribution metrics such as FID, which operate on continuous recognition features that are explicitly trained to be invariant to appearance variations, and thus discard cues critical…

Image clustering aims to partition unlabeled image datasets into distinct groups. A core aspect of this task is constructing and leveraging prior knowledge to guide the clustering process. Recent approaches introduce semantic descriptions…

Recent research has shown that integrating domain knowledge into deep learning architectures is effective -- it helps reduce the amount of required data, improves the accuracy of the models' decisions, and improves the interpretability of…

Previous works on sequential learning address the problem of forgetting in discriminative models. In this paper we consider the case of generative models. In particular, we investigate generative adversarial networks (GANs) in the task of…

As the demand for high-quality training data escalates, researchers have increasingly turned to generative models to create synthetic data, addressing data scarcity and enabling continuous model improvement. However, reliance on…

While generative modeling has become prevalent across numerous research fields, its integration into the realm of image retrieval remains largely unexplored and underjustified. In this paper, we present a novel methodology, reframing image…

Data augmentation is widely used in vision to introduce variation and mitigate overfitting, by enabling models to learn invariant properties. However, augmentation only indirectly captures these properties and does not explicitly constrain…

Graph learning algorithms have attained state-of-the-art performance on many graph analysis tasks such as node classification, link prediction, and clustering. It has, however, become hard to track the field's burgeoning progress. One…

Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider…

When it comes to classifying child sexual abuse images, managing similar inter-class correlations and diverse intra-class correlations poses a significant challenge. Vision transformer models, unlike conventional deep convolutional network…

Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing…

Novel architectures have recently improved generative image synthesis leading to excellent visual quality in various tasks. Much of this success is due to the scalability of these architectures and hence caused by a dramatic increase in…

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…

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…