Related papers: AIO2: Online Correction of Object Labels for Deep …

Following the recent advances in deep networks, object detection and tracking algorithms with deep learning backbones have been improved significantly; however, this rapid development resulted in the necessity of large amounts of annotated…

State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth…

In machine learning the best performance on a certain task is achieved by fully supervised methods when perfect ground truth labels are available. However, labels are often noisy, especially in remote sensing where manually curated public…

In this paper, we aim to improve the performance of a deep learning model towards image classification tasks, proposing a novel anchor-based training methodology, named \textit{Online Anchor-based Training} (OAT). The OAT method, guided by…

Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expensive, while the resulting labels are often subjective,…

In recent years, language-guided open-set aerial object detection has gained significant attention due to its better alignment with real-world application needs. However, due to limited datasets, most existing language-guided methods…

Developing robot perception systems for recognizing objects in the real-world requires computer vision algorithms to be carefully scrutinized with respect to the expected operating domain. This demands large quantities of ground truth data…

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet, in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part…

The enormous demand for annotated data brought forth by deep learning techniques has been accompanied by the problem of annotation noise. Although this issue has been widely discussed in machine learning literature, it has been relatively…

We present AiTLAS: Benchmark Arena -- an open-source benchmark suite for evaluating state-of-the-art deep learning approaches for image classification in Earth Observation (EO). To this end, we present a comprehensive comparative analysis…

Annotated images are required for both supervised model training and evaluation in image classification. Manually annotating images is arduous and expensive, especially for multi-labeled images. A recent trend for conducting such laboursome…

The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect…

The Unified Object Detection (UOD) task aims to achieve object detection of all merged categories through training on multiple datasets, and is of great significance in comprehensive object detection scenarios. In this paper, we conduct a…

Deep neural networks (DNNs) have demonstrated exceptional performance across various image segmentation tasks. However, the process of preparing datasets for training segmentation DNNs is both labor-intensive and costly, as it typically…

Thousands of scanned historical topographic maps contain valuable information covering long periods of time, such as how the hydrography of a region has changed over time. Efficiently unlocking the information in these maps requires…

Road infrastructure maintenance inspection is typically a labor-intensive and critical task to ensure the safety of all road users. Existing state-of-the-art techniques in Artificial Intelligence (AI) for object detection and segmentation…

High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of…

Active learning is a commonly used approach that reduces the labeling effort required to train deep neural networks. However, the effectiveness of current active learning methods is limited by their closed-world assumptions, which assume…

Document images often have intricate layout structures, with numerous content regions (e.g. texts, figures, tables) densely arranged on each page. This makes the manual annotation of layout datasets expensive and inefficient. These…

Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations. As AI systems advance and find application in safety-critical domains, effectively handling…