Related papers: Negative Token Merging: Image-based Adversarial Fe…

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…

Despite impressive recent advances in text-to-image diffusion models, obtaining high-quality images often requires prompt engineering by humans who have developed expertise in using them. In this work, we present NeuroPrompts, an adaptive…

Although text-to-image (T2I) models exhibit remarkable generation capabilities, they frequently fail to accurately bind semantically related objects or attributes in the input prompts; a challenge termed semantic binding. Previous…

Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve alignment using external rewards or human preference signals, their performance heavily…

Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer. The vast majority of such works leverages the strengths of adversarial…

The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet trained model, and transferred to change the decision of an…

Recently image-to-image translation has received increasing attention, which aims to map images in one domain to another specific one. Existing methods mainly solve this task via a deep generative model, and focus on exploring the…

We present a novel algorithm for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our method aims to generate a target image by selectively editing the regions of interest in a source image,…

Diffusion models have revolutionized generative modeling with their exceptional ability to produce high-fidelity images. However, misuse of such potent tools can lead to the creation of fake news or disturbing content targeting individuals,…

The landscape of image generation has been forever changed by open vocabulary diffusion models. However, at their core these models use transformers, which makes generation slow. Better implementations to increase the throughput of these…

Generative depth estimation methods leverage the rich visual priors stored in pre-trained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, parameter updates during training lead to catastrophic…

Adversarial attacks from generative models often produce low-quality images and require substantial computational resources. Diffusion models, though capable of high-quality generation, typically need hundreds of sampling steps for…

The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance. However, long-range dependencies are directly neglected in existing CNN fusion…

Referring Image Segmentation is a comprehensive task to segment an object referred by a textual query from an image. In nature, the level of difficulty in this task is affected by the existence of similar objects and the complexity of the…

Semantic image synthesis aims to generate high-quality images given semantic conditions, i.e. segmentation masks and style reference images. Existing methods widely adopt generative adversarial networks (GANs). GANs take all conditional…

Training an ensemble of diverse sub-models has been empirically demonstrated as an effective strategy for improving the adversarial robustness of deep neural networks. However, current ensemble training methods for image recognition…

We propose to improve text recognition from a new perspective by separating the text content from complex backgrounds. As vanilla GANs are not sufficiently robust to generate sequence-like characters in natural images, we propose an…

Large-scale text-to-image generative models have shown remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First, it is…

Contrastive Language-Image Pretraining (CLIP) has been widely used in vision tasks. Notably, CLIP has demonstrated promising performance in few-shot learning (FSL). However, existing CLIP-based methods in training-free FSL (i.e., without…

Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferability on other models…