Related papers: Labels Are Not Perfect: Inferring Spatial Uncertai…

In contrast to the incremental classification task, the incremental detection task is characterized by the presence of data ambiguity, as an image may have differently labeled bounding boxes across multiple continuous learning stages. This…

A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task. A line of research has made some progress towards this goal by studying the concentration of measure, but we argue standard…

In the past few years, object detection has attracted a lot of attention in the context of human-robot collaboration and Industry 5.0 due to enormous quality improvements in deep learning technologies. In many applications, object detection…

LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However,…

This work tackles the unsupervised cross-domain object detection problem which aims to generalize a pre-trained object detector to a new target domain without labels. We propose an uncertainty-aware model adaptation method, which is based…

Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but labels are also prone to be noisy due to human input. In this…

The image-based 3D object detection task expects that the predicted 3D bounding box has a ``tightness'' projection (also referred to as cuboid), which fits the object contour well on the image while still keeping the geometric attribute on…

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…

With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming,…

High-quality annotations are essential for object detection models, but ensuring label accuracy - especially for bounding boxes - remains both challenging and costly. This paper introduces ClipGrader, a novel approach that leverages…

In the object detection task, merging various datasets from similar contexts but with different sets of Objects of Interest (OoI) is an inexpensive way (in terms of labor cost) for crafting a large-scale dataset covering a wide range of…

Label noise is a common problem in real-world datasets, affecting both model training and validation. Clean data are essential for achieving strong performance and ensuring reliable evaluation. While various techniques have been proposed to…

We tackle semi-supervised object detection based on motion cues. Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects and use these as…

The availability of a large quantity of labelled training data is crucial for the training of modern object detectors. Hand labelling training data is time consuming and expensive while automatic labelling methods inevitably add unwanted…

The objective of augmented reality (AR) is to add digital content to natural images and videos to create an interactive experience between the user and the environment. Scene analysis and object recognition play a crucial role in AR, as…

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…

A given region in 2-D Euclidean space is divided by a unknown linear classifier in to two sets each carrying a label. The objective of an agent with known dynamics traversing the region is to identify the true classifier while paying a…

We address the problem of localisation of objects as bounding boxes in images and videos with weak labels. This weakly supervised object localisation problem has been tackled in the past using discriminative models where each object class…

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…

Most existing trackers are based on using a classifier and multi-scale estimation to estimate the target state. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While trackers adopt a…