Related papers: MaskBlur: Spatial and Angular Data Augmentation fo…
Deep Metric Learning (DML) plays an important role in modern computer vision research, where we learn a distance metric for a set of image representations. Recent DML techniques utilize the proxy to interact with the corresponding image…
Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…
Increasing the resolution of a model can improve the performance of a data assimilation system: first because model field are in better agreement with high resolution observations, then the corrections are better sustained and, with…
Shadow removal aims to restore images that are partially degraded by shadows, where the degradation is spatially localized and non-uniform. Unlike general restoration tasks that assume global degradation, shadow removal can leverage…
Recently, diffusion-based blind super-resolution (SR) methods have shown great ability to generate high-resolution images with abundant high-frequency detail, but the detail is often achieved at the expense of fidelity. Meanwhile, another…
Domain Adaptation (DA) is a method for enhancing a model's performance on a target domain with inadequate annotated data by applying the information the model has acquired from a related source domain with sufficient labeled data. The…
Due to limited size and imperfect of the optical components in a spectrometer, aberration has inevitably been brought into two-dimensional multi-fiber spectrum image in LAMOST, which leads to obvious spacial variation of the point spread…
Deep learning (DL) architectures for superresolution (SR) normally contain tremendous parameters, which has been regarded as the crucial advantage for obtaining satisfying performance. However, with the widespread use of mobile phones for…
We consider the task of self-supervised representation learning (SSL) for tabular data: tabular-SSL. Typical contrastive learning based SSL methods require instance-wise data augmentations which are difficult to design for unstructured…
Lookup table (LUT) has shown its efficacy in low-level vision tasks due to the valuable characteristics of low computational cost and hardware independence. However, recent attempts to address the problem of single image super-resolution…
Data and data sources have become increasingly essential in recent decades. Scientists and researchers require more data to deploy AI approaches as the field continues to improve. In recent years, the rapid technological advancements have…
Data assimilation (DA) improves prediction of chaotic systems by combining model forecasts with sparse, noisy observations. Many DA methods are inherently probabilistic, but accurate probabilistic DA is often computationally expensive…
We introduce a new algorithm to solve a regularized spatial-spectral image estimation problem. Our approach is based on the linearized alternating directions method of multipliers (LADMM), which is a variation of the popular ADMM algorithm.…
Unsupervised domain adaptation for LiDAR-based 3D object detection (3D UDA) based on the teacher-student architecture with pseudo labels has achieved notable improvements in recent years. Although it is quite popular to collect point clouds…
In recent years, the increasing popularity of Hi-DPI screens has driven a rising demand for high-resolution images. However, the limited computational power of edge devices poses a challenge in deploying complex super-resolution neural…
The recent use of diffusion prior, enhanced by pre-trained text-image models, has markedly elevated the performance of image super-resolution (SR). To alleviate the huge computational cost required by pixel-based diffusion SR, latent-based…
In recent years, one of the most popular techniques in the computer vision community has been the deep learning technique. As a data-driven technique, deep model requires enormous amounts of accurately labelled training data, which is often…
Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case for lidar data, for which models can exhibit large…
Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the…
Hyperspectral remote sensing images (HSIs) are characterized by having a low spatial resolution and a high spectral resolution, whereas multispectral images (MSIs) are characterized by low spectral and high spatial resolutions. These…