Related papers: Which Model Generated This Image? A Model-Agnostic…
The recent computer graphics developments have upraised the quality of the generated digital content, astonishing the most skeptical viewer. Games and movies have taken advantage of this fact but, at the same time, these advances have…
We present a generative model of images that explicitly reasons over the set of objects they show. Our model learns a structured latent representation that separates objects from each other and from the background; unlike prior works, it…
Image generation tasks are traditionally undertaken using Convolutional Neural Networks (CNN) or Transformer architectures for feature aggregating and dispatching. Despite the frequent application of convolution and attention structures,…
This paper investigates a novel problem of generating images from visual attributes. We model the image as a composite of foreground and background and develop a layered generative model with disentangled latent variables that can be…
How do language models use information provided as context when generating a response? Can we infer whether a particular generated statement is actually grounded in the context, a misinterpretation, or fabricated? To help answer these…
Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating distinctive captions that can distinguish the target…
Pretrained vision-language models, such as CLIP, show promising zero-shot performance across a wide variety of datasets. For closed-set classification tasks, however, there is an inherent limitation: CLIP image encoders are typically…
The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…
Out-of-distribution (OOD) detection is an important building block in trustworthy image recognition systems as unknown classes may arise at test-time. OOD detection methods typically revolve around a single classifier, leading to a split in…
As generative models become powerful, concerns around transparency, accountability, and copyright violations have intensified. Understanding how specific training data contributes to a model's output is critical. We introduce a framework…
Generative Models are a valuable tool for the controlled creation of high-quality image data. Controlled diffusion models like the ControlNet have allowed the creation of labeled distributions. Such synthetic datasets can augment the…
Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…
Generative models can create entirely new images, but they can also partially modify real images in ways that are undetectable to the human eye. In this paper, we address the challenge of automatically detecting such local manipulations.…
Latent generative models (e.g., Stable Diffusion) have become more and more popular, but concerns have arisen regarding potential misuse related to images generated by these models. It is, therefore, necessary to analyze the origin of…
Modern diffusion models have set the state-of-the-art in AI image generation. Their success is due, in part, to training on Internet-scale data which often includes copyrighted work. This prompts questions about the extent to which these…
Image captioning task has been extensively researched by previous work. However, limited experiments focus on generating captions based on non-autoregressive text decoder. Inspired by the recent success of the denoising diffusion model on…
We present a generative model of images based on layering, in which image layers are individually generated, then composited from front to back. We are thus able to factor the appearance of an image into the appearance of individual objects…
Recent generative models show impressive results in photo-realistic image generation. However, artifacts often inevitably appear in the generated results, leading to downgraded user experience and reduced performance in downstream tasks.…
Recent generative models produce images with a level of authenticity that makes them nearly indistinguishable from real photos and artwork. Potential harmful use cases of these models, necessitate the creation of robust synthetic image…
Few-shot OOD detection focuses on recognizing out-of-distribution (OOD) images that belong to classes unseen during training, with the use of only a small number of labeled in-distribution (ID) images. Up to now, a mainstream strategy is…