Related papers: PixelBytes: Catching Unified Representation for Mu…
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…
We present OmniBooth, an image generation framework that enables spatial control with instance-level multi-modal customization. For all instances, the multimodal instruction can be described through text prompts or image references. Given a…
Autoregressive Initial Bits is a framework that integrates sub-image autoregression and latent variable modeling, demonstrating its advantages in lossless medical image compression. However, in existing methods, the image segmentation…
Text-to-image generation models~(e.g., Stable Diffusion) have achieved significant advancements, enabling the creation of high-quality and realistic images based on textual descriptions. Prompt inversion, the task of identifying the textual…
Large Multimodal Models (LMMs) have achieved remarkable success across various visual-language tasks. However, existing benchmarks predominantly focus on single-image understanding, leaving the analysis of image sequences largely…
This paper investigates the scaling properties of autoregressive next-pixel prediction, a simple, end-to-end yet under-explored framework for unified vision models. Starting with images at resolutions of 32x32, we train a family of…
One-hot vectors, a common method for representing discrete/categorical data, in machine learning are widely used because of their simplicity and intuitiveness. However, one-hot vectors suffer from a linear increase in dimensionality, posing…
Diffusion models have recently emerged as powerful generative priors for solving inverse problems. However, training diffusion models in the pixel space are both data-intensive and computationally demanding, which restricts their…
The task of segmentation of multispectral images, which are images with numerous channels or bands, each capturing a specific range of wavelengths of electromagnetic radiation, has been previously explored in contexts with large amounts of…
Recently, biological perception has been a powerful tool for handling the camouflaged object detection (COD) task. However, most existing methods are heavily dependent on the local spatial information of diverse scales from convolutional…
Multimodal federated learning in real-world settings often encounters incomplete and heterogeneous data across clients. This results in misaligned local feature representations that limit the effectiveness of model aggregation. Unlike prior…
Probabilistic graphical models (PGMs) are widely used to discover latent structure in data, but their success hinges on selecting an appropriate model design. In practice, model specification is difficult and often requires iterative…
Audio-driven portrait animation aims to synthesize portrait videos that are conditioned by given audio. Animating high-fidelity and multimodal video portraits has a variety of applications. Previous methods have attempted to capture…
Critical aspects of computational imaging systems, such as experimental design and image priors, can be optimized through deep networks formed by the unrolled iterations of classical model-based reconstructions (termed physics-based…
It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are…
Diffusion models have recently gained state of the art performance on many image generation tasks. However, most models require significant computational resources to achieve this. This becomes apparent in the application of medical image…
In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment…
Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval…
The current state-of-the-art for image annotation and image retrieval tasks is obtained through deep neural networks, which combine an image representation and a text representation into a shared embedding space. In this paper we evaluate…
Particle filters flexibly represent multiple posterior modes nonparametrically, via a collection of weighted samples, but have classically been applied to tracking problems with known dynamics and observation likelihoods. Such generative…