Related papers: Dynamic Curriculum Learning for Great Ape Detectio…
Retail scenes usually contain densely packed high number of objects in each image. Standard object detection techniques use fully supervised training methodology. This is highly costly as annotating a large dense retail object detection…
3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to…
We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively…
Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would revolutionize our ability to study and conserve ecosystems. We investigate the ability to automatically, accurately, and…
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…
The major driving force behind the immense success of deep learning models is the availability of large datasets along with their clean labels. Unfortunately, this is very difficult to obtain, which has motivated research on the training of…
Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality…
Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes…
Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy…
Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various…
Semi-supervised learning has been well developed to help reduce the cost of manual labelling by exploiting a large quantity of unlabelled data. Especially in the application of land cover classification, pixel-level manual labelling in…
In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial…
Deep neural models have achieved state of the art performance on a wide range of problems in computer science, especially in computer vision. However, deep neural networks often require large datasets of labeled samples to generalize…
Anomaly Detection is a relevant problem that arises in numerous real-world applications, especially when dealing with images. However, there has been little research for this task in the Continual Learning setting. In this work, we…
Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on supervised learning and thus require vast amounts of training data. Due to their scarcity and minuscule…
Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on deep learning and thus require vast amounts of training data. Due to their scarcity and minuscule size,…
Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional…
Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a…
The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotations…