Related papers: A Simple Data Mixing Prior for Improving Self-Supe…

We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augmentations) obtained from images. Our work is based on two…

Diffusion models achieved unprecedented fidelity and diversity for synthesizing image, video, 3D assets, etc. However, subject mixing is an unresolved issue for diffusion-based image synthesis, particularly for synthesizing multiple…

Image reconstruction from undersampled k-space data plays an important role in accelerating the acquisition of MR data, and a lot of deep learning-based methods have been exploited recently. Despite the achieved inspiring results, the…

Image classification with deep neural networks has seen a surge of technological breakthroughs with promising applications in areas such as face recognition, medical imaging, and autonomous driving. In engineering problems, however, such as…

Deep learning architectures have achieved promising results in different areas (e.g., medicine, agriculture, and security). However, using those powerful techniques in many real applications becomes challenging due to the large labeled…

In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data…

Due to the high cost of annotation or the rarity of some diseases, medical image segmentation is often limited by data scarcity and the resulting overfitting problem. Self-supervised learning and semi-supervised learning can mitigate the…

MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural language understanding…

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Recently, MLP-like vision models have achieved promising performances on mainstream visual recognition tasks. In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations…

Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS…

Generalizable person re-identification (Re-ID) aims to recognize individuals across unseen cameras and environments. While existing methods rely heavily on limited labeled multi-camera data, we propose DynaMix, a novel method that…

Fine-grained image classification is a challenging computer vision task where various species share similar visual appearances, resulting in misclassification if merely based on visual clues. Therefore, it is helpful to leverage additional…

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks and directly applying them to Vision Transformers poses certain limitations…

Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal…

Feature matching and finding correspondences between endoscopic images is a key step in many clinical applications such as patient follow-up and generation of panoramic image from clinical sequences for fast anomalies localization.…

Online updating of the object model via samples from historical frames is of great importance for accurate visual object tracking. Recent works mainly focus on constructing effective and efficient updating methods while neglecting the…

Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human…

Advanced data augmentation strategies have widely been studied to improve the generalization ability of deep learning models. Regional dropout is one of the popular solutions that guides the model to focus on less discriminative parts by…

Data augmentation is key to improving the generalization ability of deep learning models. Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity.…