Related papers: Rethinking Feature Conditioning for Robust Forged …

Deep convolutional neural networks (CNNs) based approaches are the state-of-the-art in various computer vision tasks, including face recognition. Considerable research effort is currently being directed towards further improving deep CNNs…

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt,…

Frozen pretrained image representations are widely used for transfer learning: a backbone is kept fixed, feature vectors are extracted, and a lightweight classifier is trained on top. This pipeline usually feeds the full feature vector to…

Haze usually leads to deteriorated images with low contrast, color shift and structural distortion. We observe that many deep learning based models exhibit exceptional performance on removing homogeneous haze, but they usually fail to…

Recently, Vision Transformers (ViTs) have achieved unprecedented effectiveness in the general domain of image classification. Nonetheless, these models remain underexplored in the field of deepfake detection, given their lower performance…

Facial emotion recognition is a vast and complex problem space within the domain of computer vision and thus requires a universally accepted baseline method with which to evaluate proposed models. While test datasets have served this…

Fine-grained image recognition is a longstanding computer vision challenge that focuses on differentiating objects belonging to multiple subordinate categories within the same meta-category. Since images belonging to the same meta-category…

This paper evaluates DINOv3, a recent large-scale self-supervised vision backbone, for visuomotor diffusion policy learning in robotic manipulation. We investigate whether a purely self-supervised encoder can match or surpass conventional…

A mainstream type of the state of the arts (SOTAs) based on convolutional neural network (CNN) for real image denoising contains two sub-problems, i.e., noise estimation and non-blind denoising. This paper considers real noise approximated…

The fully convolutional network (FCN) has achieved tremendous success in dense visual recognition tasks, such as scene segmentation. The last layer of FCN is typically a global classifier (1x1 convolution) to recognize each pixel to a…

Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs, limiting deployment on resource-constrained devices. In…

We propose a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection. We leverage recent gains in large-scale object recognition by formulating the task…

Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text…

With the success of pretraining techniques in representation learning, a number of continual learning methods based on pretrained models have been proposed. Some of these methods design continual learning mechanisms on the pre-trained…

Boundary detection of irregular and translucent objects is an important problem with applications in medical imaging, environmental monitoring and manufacturing, where many of these applications are plagued with scarce labeled data and low…

Diffusion models have emerged as state-of-the-art generative methods for image synthesis, yet their potential as general-purpose feature encoders remains underexplored. Trained for denoising and generation without labels, they can be…

The proliferation of sophisticated generative models has significantly advanced the realism of synthetic facial content, known as deepfakes, raising serious concerns about digital trust. Although modern deep learning-based detectors perform…

Automatic RF modulation recognition is a primary signal intelligence (SIGINT) technique that serves as a physical layer authentication enabler and automated signal processing scheme for the beyond 5G and military networks. Most existing…

Since being introduced in 2020, Vision Transformers (ViT) has been steadily breaking the record for many vision tasks and are often described as ``all-you-need" to replace ConvNet. Despite that, ViTs are generally computational,…

Deep learning methods are notoriously data-hungry, which requires a large number of labeled samples. Unfortunately, the large amount of interactive sample labeling efforts has dramatically hindered the application of deep learning methods,…