Related papers: Semi-Supervised and Long-Tailed Object Detection w…
While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object…
Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. While techniques have been proposed to achieve a more balanced training loss and to improve tail classes data…
With the recent development of Semi-Supervised Object Detection (SS-OD) techniques, object detectors can be improved by using a limited amount of labeled data and abundant unlabeled data. However, there are still two challenges that are not…
Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to…
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…
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…
Semi-supervised object detection (SSOD) aims to boost detection performance by leveraging extra unlabeled data. The teacher-student framework has been shown to be promising for SSOD, in which a teacher network generates pseudo-labels for…
Data in real-world object detection often exhibits the long-tailed distribution. Existing solutions tackle this problem by mitigating the competition between the head and tail categories. However, due to the scarcity of training samples,…
Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training. In this paper, we propose a frustratingly simple but effective step-wise learning framework to…
Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data. Though various self-training based and consistency-regularization based SSOD…
While the pseudo-label method has demonstrated considerable success in semi-supervised object detection tasks, this paper uncovers notable limitations within this approach. Specifically, the pseudo-label method tends to amplify the inherent…
Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their…
3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to…
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a…
Semi-supervised object detection (SSOD) has made significant progress with the development of pseudo-label-based end-to-end methods. However, many of these methods face challenges due to class imbalance, which hinders the effectiveness of…
This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods. The end-to-end training gradually improves pseudo label qualities during the curriculum, and the more and…
3D object detection is an important yet demanding task that heavily relies on difficult to obtain 3D annotations. To reduce the required amount of supervision, we propose 3DIoUMatch, a novel semi-supervised method for 3D object detection…
Semi-supervised 3D object detection (SS3DOD) aims to reduce costly 3D annotations utilizing unlabeled data. Recent studies adopt pseudo-label-based teacher-student frameworks and demonstrate impressive performance. The main challenge of…
Object detection has been widely explored for class-balanced datasets such as COCO. However, real-world scenarios introduce the challenge of long-tailed distributions, where numerous categories contain only a few instances. This inherent…
Table detection, a pivotal task in document analysis, aims to precisely recognize and locate tables within document images. Although deep learning has shown remarkable progress in this realm, it typically requires an extensive dataset of…