Related papers: Deep Poisoning: Towards Robust Image Data Sharing …

Due to the high complexity and technical requirements of industrial production processes, surface defects will inevitably appear, which seriously affects the quality of products. Although existing lightweight detection networks are highly…

Diffusion Probabilistic Models (DPMs) have shown a powerful capacity of generating high-quality image samples. Recently, diffusion autoencoders (Diff-AE) have been proposed to explore DPMs for representation learning via autoencoding. Their…

Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks…

Image fusion plays a key role in a variety of multi-sensor-based vision systems, especially for enhancing visual quality and/or extracting aggregated features for perception. However, most existing methods just consider image fusion as an…

Many different deep networks have been used to approximate, accelerate or improve traditional image operators, such as image smoothing, super-resolution and denoising. Among these traditional operators, many contain parameters which need to…

Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually focus on predicting specific contents of masked patches,…

Image fusion aims to combine information from multiple source images into a single one with more comprehensive informational content. Deep learning-based image fusion algorithms face significant challenges, including the lack of a…

Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks,…

Deep neural networks are proven to be vulnerable to fine-designed adversarial examples, and adversarial defense algorithms draw more and more attention nowadays. Pre-processing based defense is a major strategy, as well as learning robust…

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…

Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…

Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems…

Personalized retrieval and segmentation aim to locate specific instances within a dataset based on an input image and a short description of the reference instance. While supervised methods are effective, they require extensive labeled data…

Deep Neural Networks (DNNs) can handle increasingly complex tasks, albeit they require rapidly expanding training datasets. Collecting data from platforms with user-generated content, such as social networks, has significantly eased the…

Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training…

Converting malware into images followed by vision-based deep learning algorithms has shown superior threat detection efficacy compared with classical machine learning algorithms. When malware are visualized as images, visual-based…

Data poisoning has been proposed as a compelling defense against facial recognition models trained on Web-scraped pictures. Users can perturb images they post online, so that models will misclassify future (unperturbed) pictures. We…

Masked visual modeling has attracted much attention due to its promising potential in learning generalizable representations. Typical approaches urge models to predict specific contents of masked tokens, which can be intuitively considered…

The current deep neural network algorithm still stays in the end-to-end training supervision method like Image-Label pairs, which makes traditional algorithm is difficult to explain the reason for the results, and the prediction logic is…

Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations,…