Related papers: Cycle Self-Training for Semi-Supervised Object Det…
Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection…
State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations. However, such 3D annotations are often expensive and time-consuming, which may not be practical for real applications. A…
Source-free object detection (SFOD) aims to adapt the source detector to unlabeled target domain data in the absence of source domain data. Most SFOD methods follow the same self-training paradigm using mean-teacher (MT) framework where the…
Object detection for autonomous vehicles has received increasing attention in recent years, where labeled data are often expensive while unlabeled data can be collected readily, calling for research on semi-supervised learning for this…
Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, has made significant progress recently. However, existing works have primarily focused on image classification tasks and neglected object detection…
Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via…
Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, i.e., generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. Although they achieved certain success, the limited…
Neural networks have demonstrated exceptional performance in supervised learning, benefiting from abundant high-quality annotated data. However, obtaining such data in real-world scenarios is costly and labor-intensive. Semi-supervised…
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…
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…
Due to the high cost of collection and labeling, there are relatively few datasets for camouflaged object detection (COD). In particular, for certain specialized categories, the available image dataset is insufficiently populated. Synthetic…
Entity alignment is to find identical entities in different knowledge graphs. Although embedding-based entity alignment has recently achieved remarkable progress, training data insufficiency remains a critical challenge. Conventional…
Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that…
In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object…
We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training…
In object detection, unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, UDA's reliance on labeled source data restricts its adaptability in privacy-related…
Semi-Supervised Object Detection (SSOD) has achieved resounding success by leveraging unlabeled data to improve detection performance. However, in Open Scene Semi-Supervised Object Detection (O-SSOD), unlabeled data may contains unknown…
Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…
Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object…
Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To…