Related papers: Free-ATM: Exploring Unsupervised Learning on Diffu…
Many leading self-supervised methods for unsupervised representation learning, in particular those for embedding image features, are built on variants of the instance discrimination task, whose optimization is known to be prone to…
Generative models have been very popular in the recent years for their image generation capabilities. GAN-based models are highly regarded for their disentangled latent space, which is a key feature contributing to their success in…
Image translation between two domains is a class of problems aiming to learn mapping from an input image in the source domain to an output image in the target domain. It has been applied to numerous domains, such as data augmentation,…
Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…
Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats generated tokens as immutable, which may lead to error…
Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…
Semantic segmentation is a computer vision task where classification is performed at a pixel level. Due to this, the process of labeling images for semantic segmentation is time-consuming and expensive. To mitigate this cost there has been…
Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts. However, increasing research indicates that these models memorize and replicate images…
Diffusion models achieved unprecedented fidelity and diversity for synthesizing image, video, 3D assets, etc. However, subject mixing is an unresolved issue for diffusion-based image synthesis, particularly for synthesizing multiple…
As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright protection and ensuring model transparency. Existing methods achieve this attribution…
While recent developments in text-to-image generative models have led to a suite of high-performing methods capable of producing creative imagery from free-form text, there are several limitations. By analyzing the cross-attention…
Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…
Text-to-image (T2I) diffusion models, with their impressive generative capabilities, have been adopted for image editing tasks, demonstrating remarkable efficacy. However, due to attention leakage and collision between the cross-attention…
Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene. Motivated by the important role of…
The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…
There has been a longstanding belief that generation can facilitate a true understanding of visual data. In line with this, we revisit generatively pre-training visual representations in light of recent interest in denoising diffusion…
A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the image in the latent space of the pretrained model. However,…
Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning…
Conditional diffusion models can create unseen images in various settings, aiding image interpolation. Interpolation in latent spaces is well-studied, but interpolation with specific conditions like text or poses is less understood. Simple…
Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled…