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 …

In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised
object detection (SSOD). Our core observation is that the oscillating pseudo-targets …

Abstract Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for
boosting object detectors, has become an active task in recent years. However, existing …

Abstract With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage
detectors generally obtain limited promotions compared with two-stage clusters. We …

Semi-Supervised Object Detection (SSOD) has been successful in improving the
performance of both R-CNN series and anchor-free detectors. However, one-stage anchor …

Artificial Intelligence of Things (AIoT) is an emerging frontier based on the deep fusion of
Internet of Things (IoT) and Artificial Intelligence (AI) technologies. The fundamental goal of …

In recent years, deep learning technology has been maturely applied in the field of object
detection, and most algorithms tend to be supervised learning. However, a large amount of …

Semi-supervised object detection (SSOD) attracts extensive research interest due to its great
significance in reducing the data annotation effort. Collecting high-quality and category …

Current semi-supervised object detection (SSOD) algorithms typically assume class
balanced datasets (PASCAL VOC etc.) or slightly class imbalanced datasets (MSCOCO …

This paper focuses on long-tailed object detection in the semi-supervised learning setting,
which poses realistic challenges, but has rarely been studied in the literature. We propose a …