Related papers: Exploring Local Memorization in Diffusion Models v…
Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting…
End-to-end scene text spotting, which unifies text detection and recognition within a single framework, has witnessed remarkable progress driven by deep learning advances. However, most existing approaches still suffer from incomplete mask…
Diffusion-based Image Editing (DIE) is an emerging research hot-spot, which often applies a semantic mask to control the target area for diffusion-based editing. However, most existing solutions obtain these masks via manual operations or…
Despite the empirical advances of deep learning across a variety of learning tasks, our theoretical understanding of its success is still very restricted. One of the key challenges is the overparametrized nature of modern models, enabling…
There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a…
We propose an effective method for inserting adapters into text-to-image foundation models, which enables the execution of complex downstream tasks while preserving the generalization ability of the base model. The core idea of this method…
Visual perception is critically influenced by the focus of attention. Due to limited resources, it is well known that neural representations are biased in favor of attended locations. Using concurrent eye-tracking and functional Magnetic…
Recent efforts at explaining the interplay of memorization and generalization in deep overparametrized networks have posited that neural networks $\textit{memorize}$ "hard" examples in the final few layers of the model. Memorization refers…
Text-to-image diffusion models rely on text embeddings from a pre-trained text encoder, but these embeddings remain fixed across all diffusion timesteps, limiting their adaptability to the generative process. We propose Diffusion Adaptive…
Recently, the application of deep learning in image colorization has received widespread attention. The maturation of diffusion models has further advanced the development of image colorization models. However, current mainstream image…
Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…
In this paper we present the design and evaluation of an end-to-end trainable, deep neural network with a visual attention mechanism for memorability estimation in still images. We analyze the suitability of transfer learning of deep models…
We present TALE, a novel training-free framework harnessing the generative capabilities of text-to-image diffusion models to address the cross-domain image composition task that focuses on flawlessly incorporating user-specified objects…
Text-based image editing, powered by generative diffusion models, lets users modify images through natural-language prompts and has dramatically simplified traditional workflows. Despite these advances, current methods still suffer from a…
Precise spatial control in diffusion-based style transfer remains challenging. This challenge arises because diffusion models treat style as a global feature and lack explicit spatial grounding of style representations, making it difficult…
Overfitting in deep neural networks occurs less frequently than expected. This is a puzzling observation, as theory predicts that greater model capacity should eventually lead to overfitting -- yet this is rarely seen in practice. But what…
The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry. The significant advances in text-to-image generation techniques have prompted global discussions on privacy,…
Recent advances in text-to-image diffusion models have substantially improved the quality of image customization, enabling the synthesis of highly realistic images. Despite this progress, achieving fast and efficient personalization remains…
We propose a novel recurrent attentional structure to localize and recognize objects jointly. The network can learn to extract a sequence of local observations with detailed appearance and rough context, instead of sliding windows or…
Text spotting in natural scene images is of great importance for many image understanding tasks. It includes two sub-tasks: text detection and recognition. In this work, we propose a unified network that simultaneously localizes and…