Related papers: LabelEnc: A New Intermediate Supervision Method fo…

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…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

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…

Object detection with event cameras benefits from the sensor's low latency and high dynamic range. However, it is costly to fully label event streams for supervised training due to their high temporal resolution. To reduce this cost, we…

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…

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…

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…

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…

Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy…

Passive methods for object detection and segmentation treat images of the same scene as individual samples and do not exploit object permanence across multiple views. Generalization to novel or difficult viewpoints thus requires additional…

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…

We propose a method, called Label Embedding Network, which can learn label representation (label embedding) during the training process of deep networks. With the proposed method, the label embedding is adaptively and automatically learned…

Various strategies for label-scarce object detection have been explored by the computer vision research community. These strategies mainly rely on assumptions that are specific to natural images and not directly applicable to the biological…

Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous…

Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes…

Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object…

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,…

We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework. Our method is featured with 1) the exponential moving averaging strategy to update the teacher from the student…