Related papers: Dense Teacher: Dense Pseudo-Labels for Semi-superv…

Semi-supervised 3D object detection is a promising yet under-explored direction to reduce data annotation costs, especially for cluttered indoor scenes. A few prior works, such as SESS and 3DIoUMatch, attempt to solve this task by utilizing…

Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain…

Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented…

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training an…

Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends…

Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data. Although there has been remarkable recent progress, the scope of demonstration in SSL has mainly been on…

Deep learning is pushing the state-of-the-art in many computer vision applications. However, it relies on large annotated data repositories, and capturing the unconstrained nature of the real-world data is yet to be solved. Semi-supervised…

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…

Few-shot object detection (FSOD) is a challenging problem aimed at detecting novel concepts from few exemplars. Existing approaches to FSOD all assume abundant base labels to adapt to novel objects. This paper studies the new task of…

To ensure safe urban driving for autonomous platforms, it is crucial not only to develop high-performance object detection techniques but also to establish a diverse and representative dataset that captures various urban environments and…

The success of existing salient object detection models relies on a large pixel-wise labeled training dataset, which is time-consuming and expensive to obtain. We study semi-supervised salient object detection, with access to a small number…

Effective waste sorting is critical for sustainable recycling, yet AI research in this domain continues to lag behind commercial systems due to limited datasets and reliance on legacy object detectors. In this work, we advance AI-driven…

Recent open-vocabulary detection methods aim to detect novel objects by distilling knowledge from vision-language models (VLMs) trained on a vast amount of image-text pairs. To improve the effectiveness of these methods, researchers have…

Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent…

Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain.…

In real-world applications, an object detector often encounters object instances from new classes and needs to accommodate them effectively. Previous work formulated this critical problem as incremental object detection (IOD), which assumes…

Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations. In this paper, we focus on a practical scenario that one aims to apply SSL when unlabeled data may contain…

Lacking supervised data is an issue while training deep neural networks (DNNs), mainly when considering medical and biological data where supervision is expensive. Recently, Embedded Pseudo-Labeling (EPL) addressed this problem by using a…

Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning…

In the field of Class Incremental Object Detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenario incremental learning…