Related papers: Harnessing Massive Satellite Imagery with Efficien…

Intelligent fetal ultrasound (US) interpretation is crucial for prenatal diagnosis, but high annotation costs and operator-induced variance make unsupervised pre-training a highly promising paradigm. However, existing pre-training methods…

High-resolution semantic segmentation is essential for applications such as image editing, bokeh imaging, AR/VR, etc. Unfortunately, existing datasets often have limited resolution and lack precise mask details and boundaries. In this work,…

Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typically inferior to competing approaches. Most users cannot…

Learned image compression (LIC) methods have experienced significant progress during recent years. However, these methods are primarily dedicated to optimizing the rate-distortion (R-D) performance at medium and high bitrates (> 0.1 bits…

Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…

Text-to-image retrieval (TIR) aims to find relevant images based on a textual query, but existing approaches are primarily based on whole-image captions and lack interpretability. Meanwhile, referring expression segmentation (RES) enables…

Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is…

Learning representations through self-supervision on unlabeled data has proven highly effective for understanding diverse images. However, remote sensing images often have complex and densely populated scenes with multiple land objects and…

Understanding vehicles in images is important for various applications such as intelligent transportation and self-driving system. Existing vehicle-centric works typically pre-train models on large-scale classification datasets and then…

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…

Coronal mass ejections (CMEs) are a major driver of space weather. To assess CME geoeffectiveness, among other scientific goals, it is necessary to reliably identify and characterize their morphology and kinematics in coronagraph images.…

Vehicle-centric perception plays a crucial role in many intelligent systems, including large-scale surveillance systems, intelligent transportation, and autonomous driving. Existing approaches lack effective learning of vehicle-related…

Mass spectrometry imaging (MSI) enables label-free visualization of molecular distributions across tissue samples but generates large and complex datasets that require effective peak picking to reduce data size while preserving meaningful…

We propose ADIOS, a masked image model (MIM) framework for self-supervised learning, which simultaneously learns a masking function and an image encoder using an adversarial objective. The image encoder is trained to minimise the distance…

Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial images as described by textual queries. Traditional Referring Image…

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…

Both masked image modeling (MIM) and natural language supervision have facilitated the progress of transferable visual pre-training. In this work, we seek the synergy between two paradigms and study the emerging properties when MIM meets…

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible…

While Masked Image Modeling (MIM) has revolutionized fields of computer vision, its adoption in 3D medical image computing has been limited by the use of random masking, which overlooks the density of anatomical objects. To address this…

Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure…