相关论文: Mitigating representation bias caused by missing p…

In many real-world binary classification tasks (e.g. detection of certain objects from images), an available dataset is imbalanced, i.e., it has much less representatives of a one class (a minor class), than of another. Generally, accurate…

Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative information of a fine-grained image usually resides in…

Image classification benchmark datasets such as CIFAR, MNIST, and ImageNet serve as critical tools for model evaluation. However, despite the cleaning efforts, these datasets still suffer from pervasive noisy labels and often contain…

In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels. Recently, graph-based methods, which demonstrate a good ability…

Image classification is often prone to labelling uncertainty. To generate suitable training data, images are labelled according to evaluations of human experts. This can result in ambiguities, which will affect subsequent models. In this…

The learning from imbalanced data is a deeply studied problem in standard classification and, in recent times, also in multilabel classification. A handful of multilabel resampling methods have been proposed in late years, aiming to balance…

Semi-supervised learning is a powerful technique for leveraging unlabeled data to improve machine learning models, but it can be affected by the presence of ``informative'' labels, which occur when some classes are more likely to be labeled…

Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…

Snapshot mosaic multispectral imagery acquires an undersampled data cube by acquiring a single spectral measurement per spatial pixel. Sensors which acquire $p$ frequencies, therefore, suffer from severe $1/p$ undersampling of the full data…

Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization. Existing attribute learning methods often treat the missing labels as negative or simply ignore them all during…

Image classification is a challenging problem for computer in reality. Large numbers of methods can achieve satisfying performances with sufficient labeled images. However, labeled images are still highly limited for certain image…

This paper presents a novel Bayesian approach for hyperspectral image unmixing. The observed pixels are modeled by a linear combination of material signatures weighted by their corresponding abundances. A spike-and-slab abundance prior is…

Missing values are largely inevitable in gene expression microarray studies. Data sets often have significant omissions due to individuals dropping out of experiments, errors in data collection, image corruptions, and so on. Missing data…

This paper strives to address image classifier bias, with a focus on both feature and label embedding spaces. Previous works have shown that spurious correlations from protected attributes, such as age, gender, or skin tone, can cause…

Spectral-spatial classification of hyperspectral images has been the subject of many studies in recent years. In the presence of only very few labeled pixels, this task becomes challenging. In this paper we address the following two…

We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation…

Imperfect labels limit the quality of predictions learned by deep neural networks. This is particularly relevant in medical image segmentation, where reference annotations are difficult to collect and vary significantly even across expert…

Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…

Deep learning identification models have shown promise for identifying gas plumes in Longwave IR hyperspectral images of urban scenes, particularly when a large library of gases are being considered. Because many gases have similar spectral…

Chemicals released in the air can be extremely dangerous for human beings and the environment. Hyperspectral images can be used to identify chemical plumes, however the task can be extremely challenging. Assuming we know a priori that some…