Related papers: Multi-Class 3D Object Detection with Single-Class …

Deep Learning (DL) based methods for object detection achieve remarkable performance at the cost of computationally expensive training and extensive data labeling. Robots embodiment can be exploited to mitigate this burden by acquiring…

Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance by only selecting…

Semi-supervised 3D medical image segmentation aims to achieve accurate segmentation using few labelled data and numerous unlabelled data. The main challenge in the design of semi-supervised learning methods consists in the effective use of…

Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…

Supervised learning techniques are at the center of many tasks in remote sensing. Unfortunately, these methods, especially recent deep learning methods, often require large amounts of labeled data for training. Even though satellites…

Existing semi-supervised learning (SSL) methods assume that labeled and unlabeled data share the same class space. However, in real-world applications, unlabeled data always contain classes not present in the labeled set, which may cause…

Deep learning has attained remarkable success in many 3D visual recognition tasks, including shape classification, object detection, and semantic segmentation. However, many of these results rely on manually collecting densely annotated…

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…

Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features…

Compared to 2D lanes, real 3D lane data is difficult to collect accurately. In this paper, we propose a novel method for training 3D lanes with only 2D lane labels, called weakly supervised 3D lane detection WS-3D-Lane. By assumptions of…

Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against. A common property among its various methods is that they…

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels,…

Recent developments for Semi-Supervised Object Detection (SSOD) have shown the promise of leveraging unlabeled data to improve an object detector. However, thus far these methods have assumed that the unlabeled data does not contain…

Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation cost, e.g., 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we propose a framework to study how to leverage constraints…

In the fast-evolving field of artificial intelligence, where models are increasingly growing in complexity and size, the availability of labeled data for training deep learning models has become a significant challenge. Addressing complex…

Scale variation across object instances remains a key challenge in object detection task. Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case. While existing…

I present the Lower Biased Teacher model, an enhancement of the Unbiased Teacher model, specifically tailored for semi-supervised object detection tasks. The primary innovation of this model is the integration of a localization loss into…

Self-Supervised Learning (SSL) has emerged as a promising approach in computer vision, enabling networks to learn meaningful representations from large unlabeled datasets. SSL methods fall into two main categories: instance discrimination…

In this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher(Source code are available at: \url{https://github.com/HunterJ-Lin/ActiveTeacher}) for…

We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-visual data, using…