Related papers: Dual form Complementary Masking for Domain-Adaptiv…

Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain. The majority of existing UDA-SS works typically consider images whilst recent attempts…

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…

Masked image modeling, an emerging self-supervised pre-training method, has shown impressive success across numerous downstream vision tasks with Vision transformers. Its underlying idea is simple: a portion of the input image is masked out…

Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases…

Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow…

Masked (or absorbing) diffusion is actively explored as an alternative to autoregressive models for generative modeling of discrete data. However, existing work in this area has been hindered by unnecessarily complex model formulations and…

As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapted to real images without requiring their annotations. This…

Facial Action Units (AUs) are essential for conveying psychological states and emotional expressions. While automatic AU detection systems leveraging deep learning have progressed, they often overfit to specific datasets and individual…

The recent person re-identification research has achieved great success by learning from a large number of labeled person images. On the other hand, the learned models often experience significant performance drops when applied to images…

Medical image segmentation plays a crucial role in clinical workflows, but domain shift often leads to performance degradation when models are applied to unseen clinical domains. This challenge arises due to variations in imaging…

Magnetic Resonance Imaging (MRI) is widely used in clinical practice, but suffered from prolonged acquisition time. Although deep learning methods have been proposed to accelerate acquisition and demonstrate promising performance, they rely…

Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be…

Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps. Recently, there has been a growing interest in…

An increasing number of classification approaches have been developed to address the issue of image rebroadcast and recapturing, a standard attack strategy in insurance frauds, face spoofing, and video piracy. However, most of them…

Lesion segmentation, in contrast to natural scene segmentation, requires handling subtle variations in texture and color, frequent imaging artifacts (such as hairs, rulers, and bubbles), and a critical need for precise boundary localization…

Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial. Though U-shaped encoder-decoder frameworks have been witnessed to be successful, most of them share a common…

Although deep convolutional networks have achieved great performance in face recognition tasks, the challenge of domain discrepancy still exists in real world applications. Lack of domain coverage of training data (source domain) makes the…

Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neural networks. However, existing diffusion-based counterfactual…

Deep learning based medical image segmentation models usually require large datasets with high-quality dense segmentations to train, which are very time-consuming and expensive to prepare. One way to tackle this challenge is by using the…

3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction.…