Related papers: Conditional Hallucinations for Image Compression

Contemporary face hallucination (FH) models exhibit considerable ability to reconstruct high-resolution (HR) details from low-resolution (LR) face images. This ability is commonly learned from examples of corresponding HR-LR image pairs,…

Learned image compression codecs have recently achieved impressive compression performances surpassing the most efficient image coding architectures. However, most approaches are trained to minimize rate and distortion which often leads to…

Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are…

Denoising diffusion models achieved impressive results on several image generation tasks often outperforming GAN based models. Recently, the generative capabilities of diffusion models have been employed for perceptual image compression,…

Hallucinations in Large Language Models (LLMs) pose a major barrier to their reliable use in critical decision-making. Although existing hallucination detection methods have improved accuracy, they still struggle with disentangling semantic…

Generative super-resolution (GSR) currently sets the state-of-the-art in terms of perceptual image quality, overcoming the "regression-to-the-mean" blur of prior non-generative models. However, from a human perspective, such models do not…

Large language models often hallucinate with high confidence on "random facts" that lack inferable patterns. We formalize the memorization of such facts as a membership testing problem, unifying the discrete error metrics of Bloom filters…

While recent years have seen rapid progress in image-conditioned text generation, image captioning still suffers from the fundamental issue of hallucinations, namely, the generation of spurious details that cannot be inferred from the given…

While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate,…

Contrastive learning models based on Siamese structure have demonstrated remarkable performance in self-supervised learning. Such a success of contrastive learning relies on two conditions, a sufficient number of positive pairs and adequate…

Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing…

Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on errors in the training data. In this work, we propose a new method called Contrastive Parameter…

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

In this paper we present an end-to-end meta-learned system for image compression. Traditional machine learning based approaches to image compression train one or more neural network for generalization performance. However, at inference…

Neural conditional language generation models achieve the state-of-the-art in Neural Machine Translation (NMT) but are highly dependent on the quality of parallel training dataset. When trained on low-quality datasets, these models are…

Neural compression has the potential to revolutionize lossy image compression. Based on generative models, recent schemes achieve unprecedented compression rates at high perceptual quality but compromise semantic fidelity. Details of…

In recent years, there has been rapid development in learned image compression techniques that prioritize ratedistortion-perceptual compression, preserving fine details even at lower bit-rates. However, current learning-based image…

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help…

Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitations in existing attention mechanisms and insufficient…

Tomographic image reconstruction is generally an ill-posed linear inverse problem. Such ill-posed inverse problems are typically regularized using prior knowledge of the sought-after object property. Recently, deep neural networks have been…