相关论文: Revisiting the Encoding of Satellite Image Time Se…

Modern change detection (CD) has achieved remarkable success by the powerful discriminative ability of deep convolutions. However, high-resolution remote sensing CD remains challenging due to the complexity of objects in the scene. Objects…

Instance segmentation of remote sensing images (RSIs) is an essential task for a wide range of applications such as land planning and intelligent transport. Instance segmentation of RSIs is constantly plagued by the unbalanced ratio of…

Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of…

Synthetic aperture sonar (SAS) image resolution is constrained by waveform bandwidth and array geometry. Specifically, the waveform bandwidth determines a point spread function (PSF) that blurs the locations of point scatterers in the…

We present a framework to translate between 2D image views and 3D object shapes. Recent progress in deep learning enabled us to learn structure-aware representations from a scene. However, the existing literature assumes that pairs of…

Self-supervised Learning (SSL) has been widely applied to learn image representations through exploiting unlabeled images. However, it has not been fully explored in the medical image analysis field. In this work, Saliency-guided…

Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost. In this paper, we present STTS, a token selection framework that dynamically selects a few…

Recent methods for neural surface representation and rendering, for example NeuS, have demonstrated the remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8 hours), which…

The most recent year has witnessed the success of applying the Vision Transformer (ViT) for image classification. However, there are still evidences indicating that ViT often suffers following two aspects, i) the high computation and the…

In this paper, we present an innovative approach to self-supervised learning for Vision Transformers (ViTs), integrating local masked image modeling with progressive layer freezing. This method focuses on enhancing the efficiency and speed…

Multivariate time-series data are frequently observed in critical care settings and are typically characterized by sparsity (missing information) and irregular time intervals. Existing approaches for learning representations in this domain…

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive…

Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by distilling the current knowledge and incorporating the latest…

Weakly-supervised image segmentation (WSIS) is a critical task in computer vision that relies on image-level class labels. Multi-stage training procedures have been widely used in existing WSIS approaches to obtain high-quality pseudo-masks…

Many studies have concentrated on constructing supervised models utilizing paired datasets for image denoising, which proves to be expensive and time-consuming. Current self-supervised and unsupervised approaches typically rely on…

Spatial-temporal forecasting is crucial and widely applicable in various domains such as traffic, energy, and climate. Benefiting from the abundance of unlabeled spatial-temporal data, self-supervised methods are increasingly adapted to…

Due to the difficulty of replicating the real conditions during training, supervised algorithms for spacecraft pose estimation experience a drop in performance when trained on synthetic data and applied to real operational data. To address…

The deployment of reconfigurable intelligent surfaces (RISs) in a communication system provides control over the propagation environment, which facilitates the augmentation of a multitude of communication objectives. As these performance…

Several interpretability methods for convolutional network-based classifiers exist. Most of these methods focus on extracting saliency maps for a given sample, providing a local explanation that highlights the main regions for the…

European satellite missions Sentinel-1 (S1) and Sentinel-2 (S2) provide at highspatial resolution and high revisit time, respectively, radar and optical imagesthat support a wide range of Earth surface monitoring tasks such as LandUse/Land…