Related papers: APPLE: Attribute-Preserving Pseudo-Labeling for Di…

Spurious features associated with class labels can lead image classifiers to rely on shortcuts that don't generalize well to new domains. This is especially problematic in medical settings, where biased models fail when applied to different…

Face editing methods, essential for tasks like virtual avatars, digital human synthesis and identity preservation, have traditionally been built upon GAN-based techniques, while recent focus has shifted to diffusion-based models due to…

Object swapping aims to replace a source object in a scene with a reference object while preserving object fidelity, scene fidelity, and object-scene harmony. Existing methods either require per-object finetuning and slow inference or rely…

Semantically consistent cross-domain image translation facilitates the generation of training data by transferring labels across different domains, making it particularly useful for plant trait identification in agriculture. However,…

Supervised deep learning for semantic segmentation has achieved excellent results in accurately identifying anatomical and pathological structures in medical images. However, it often requires large annotated training datasets, which limits…

Current face de-identification methods that replace identifiable cues in the face region with other sacrifices utilities contributing to realism, such as age and gender. To retrieve the damaged realism, we present FLUID (Face…

With the rapid development of face recognition (FR) systems, the privacy of face images on social media is facing severe challenges due to the abuse of unauthorized FR systems. Some studies utilize adversarial attack techniques to defend…

Unsupervised domain adaptation reduces the reliance on data annotation in deep learning by adapting knowledge from a source to a target domain. For privacy and efficiency concerns, source-free domain adaptation extends unsupervised domain…

Exposure correction is essential for enhancing image quality under challenging lighting conditions. While supervised learning has achieved significant progress in this area, it relies heavily on large-scale labeled datasets, which are…

Learning from ambiguous labels is a long-standing problem in practical machine learning applications. The purpose of \emph{partial label learning} (PLL) is to identify the ground-truth label from a set of candidate labels associated with a…

Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned…

In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…

Similar to facial beautification in real life, 3D virtual avatars require personalized customization to enhance their visual appeal, yet this area remains insufficiently explored. Although current 3D Gaussian editing methods can be adapted…

We present a methodology for conditional control of human shape and pose in pretrained text-to-image diffusion models using a 3D human parametric model (SMPL). Fine-tuning these diffusion models to adhere to new conditions requires large…

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…

Augmentation for dense prediction typically relies on either sample mixing or generative synthesis. Mixing improves robustness but misaligned masks yield soft label ambiguity. Diffusion synthesis increases apparent diversity but, when…

Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such significant portion results in insufficient training data.…

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…

We present a training-free, plug-and-play method, namely VFace, for high-quality face swapping in videos. It can be seamlessly integrated with image-based face swapping approaches built on diffusion models. First, we introduce a Frequency…

Facial appearance editing is crucial for digital avatars, AR/VR, and personalized content creation, driving realistic user experiences. However, preserving identity with generative models is challenging, especially in scenarios with limited…