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

Cloud analysis is a critical component of weather and climate science, impacting various sectors like disaster management. However, achieving fine-grained cloud analysis, such as cloud segmentation, in remote sensing remains challenging due…

High-quality data is necessary for modern machine learning. However, the acquisition of such data is difficult due to noisy and ambiguous annotations of humans. The aggregation of such annotations to determine the label of an image leads to…

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…

Deep neural networks deliver state-of-the-art visual recognition, but they rely on large datasets, which are time-consuming to annotate. These datasets are typically annotated in two stages: (1) determining the presence of object classes at…

Semi-supervised 3D object detection can benefit from the promising pseudo-labeling technique when labeled data is limited. However, recent approaches have overlooked the impact of noisy pseudo-labels during training, despite efforts to…

This technical report describes our system that is submitted to the Deep Noise Suppression Challenge and presents the results for the non-real-time track. To refine the estimation results stage by stage, we utilize recursive learning, a…

Object detection using LiDAR point clouds relies on a large amount of human-annotated samples when training the underlying detectors' deep neural networks. However, generating 3D bounding box annotation for a large-scale dataset could be…

3D object detection is an important yet demanding task that heavily relies on difficult to obtain 3D annotations. To reduce the required amount of supervision, we propose 3DIoUMatch, a novel semi-supervised method for 3D object detection…

3D object detection networks tend to be biased towards the data they are trained on. Evaluation on datasets captured in different locations, conditions or sensors than that of the training (source) data results in a drop in model…

Recent works of opinion expression identification (OEI) rely heavily on the quality and scale of the manually-constructed training corpus, which could be extremely difficult to satisfy. Crowdsourcing is one practical solution for this…

Crowdsourcing platforms offer a practical solution to the problem of affordably annotating large datasets for training supervised classifiers. Unfortunately, poor worker performance frequently threatens to compromise annotation reliability,…

Active learning (AL), which iteratively queries the most informative examples from a large pool of unlabeled candidates for model training, faces significant challenges in the presence of open-set classes. Existing methods either prioritize…

Fully supervised object detection requires training images in which all instances are annotated. This is actually impractical due to the high labor and time costs and the unavoidable missing annotations. As a result, the incomplete…

An accurate and substantial dataset is essential for training a reliable and well-performing model. However, even manually annotated datasets contain label errors, not to mention automatically labeled ones. Previous methods for label…

Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literature (with several recent exceptions) of learning with noisy…

This paper presents an AI-assisted auto-labeling system for display panel defect detection that leverages in-context learning capabilities. We adopt and enhance the SegGPT architecture with several domain-specific training techniques and…

In recent years, deep learning techniques (e.g., U-Net, DeepLab) have achieved tremendous success in image segmentation. The performance of these models heavily relies on high-quality ground truth segment labels. Unfortunately, in many…

Data from satellites or aerial vehicles are most of the times unlabelled. Annotating such data accurately is difficult, requires expertise, and is costly in terms of time. Even if Earth Observation (EO) data were correctly labelled, labels…

Multi-class cell segmentation in high-resolution gigapixel whole slide images (WSIs) is crucial for various clinical applications. However, training such models typically requires labor-intensive, pixel-wise annotations by domain experts.…

Manual annotation of soiling on surround view cameras is a very challenging and expensive task. The unclear boundary for various soiling categories like water drops or mud particles usually results in a large variance in the annotation…