Related papers: MiSiSUn: Minimum Simplex Semisupervised Unmixing
RGB-D scene parsing methods effectively capture both semantic and geometric features of the environment, demonstrating great potential under challenging conditions such as extreme weather and low lighting. However, existing RGB-D scene…
Deep learning-based (DL-based) hyperspectral image (HIS) super-resolution (SR) methods have achieved remarkable performance and attracted attention in industry and academia. Nonetheless, most current methods explored and learned the mapping…
Deep neural networks tend to memorize noisy labels, severely degrading their generalization performance. Although Mixup has demonstrated effectiveness in improving generalization and robustness, existing Mixup-based methods typically…
In blind hyperspectral unmixing (HU), the pure-pixel assumption is well-known to be powerful in enabling simple and effective blind HU solutions. However, the pure-pixel assumption is not always satisfied in an exact sense, especially for…
We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions…
Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to…
Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding. From an…
We consider the problem of super-resolving the line spectrum of a multisinusoidal signal from a finite number of samples, some of which may be completely corrupted. Measurements of this form can be modeled as an additive mixture of a…
The democratization of Data Mining has been widely successful thanks in part to powerful and easy-to-use Machine Learning libraries. These libraries have been particularly tailored to tackle Supervised Learning. However, strong supervision…
Semi-supervised learning has received considerable attention for its potential to leverage abundant unlabeled data to enhance model robustness. Pseudo labeling is a widely used strategy in semi supervised learning. However, existing methods…
Fusing a low resolution (LR) mosaiced hyperspectral image (HSI) with a high resolution (HR) panchromatic (PAN) image offers a promising avenue for video-rate HR-HSI imaging via single-shot acquisition, yet its severely ill-posed nature…
In a recent paper, we have proposed an unsupervised algorithm for audio signal segmentation entirely based on Bayesian methods. In its first implementation, however, the method showed poor computational performance. In this paper we address…
For many machine learning tasks, the input data lie on a low-dimensional manifold embedded in a high dimensional space and, because of this high-dimensional structure, most algorithms are inefficient. The typical solution is to reduce the…
We revisit the source image estimation problem from blind source separation (BSS). We generalize the traditional minimum distortion principle to maximum likelihood estimation with a model for the residual spectrograms. Because residual…
We propose a new framework, called Poisson learning, for graph based semi-supervised learning at very low label rates. Poisson learning is motivated by the need to address the degeneracy of Laplacian semi-supervised learning in this regime.…
Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific selection mechanisms to separate clean and noisy samples and…
This paper proposes a novel algorithm for semisupervised learning. This algorithm learns graph cuts that maximize the margin with respect to the labels induced by the harmonic function solution. We motivate the approach, compare it to…
Hyperspectral salient object detection (HSOD) has exhibited remarkable promise across various applications, particularly in intricate scenarios where conventional RGB-based approaches fall short. Despite the considerable progress in HSOD…
Data augmentation is now an essential part of the image training process, as it effectively prevents overfitting and makes the model more robust against noisy datasets. Recent mixing augmentation strategies have advanced to generate the…
We propose the first unified theoretical analysis of mixed sample data augmentation (MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level…