Related papers: A denoised Mean Teacher for domain adaptive point …

Domain Generalization (DG) seeks to transfer knowledge from multiple source domains to unseen target domains, even in the presence of domain shifts. Achieving effective generalization typically requires a large and diverse set of labeled…

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…

We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain. The majority of approaches for the problem employ a…

Tiny objects, with their limited spatial resolution, often resemble point-like distributions. As a result, bounding box prediction using point-level supervision emerges as a natural and cost-effective alternative to traditional box-level…

Gait recognition is an emerging identification technology that distinguishes individuals at long distances by analyzing individual walking patterns. Traditional techniques rely heavily on large-scale labeled datasets, which incurs high…

Recently proposed techniques for semi-supervised learning such as Temporal Ensembling and Mean Teacher have achieved state-of-the-art results in many important classification benchmarks. In this work, we expand the Mean Teacher approach to…

Source-Free Domain Adaptation (SFDA) is emerging as a compelling solution for medical image segmentation under privacy constraints, yet current approaches often ignore sample difficulty and struggle with noisy supervision under domain…

Non-rigid registration is a necessary but challenging task in medical imaging studies. Recently, unsupervised registration models have shown good performance, but they often require a large-scale training dataset and long training times.…

Earlier work demonstrates the promise of deep-learning-based approaches for point cloud segmentation; however, these approaches need to be improved to be practically useful. To this end, we introduce a new model SqueezeSegV2 that is more…

Semantic segmentation is a crucial task in medical imaging. Although supervised learning techniques have proven to be effective in performing this task, they heavily depend on large amounts of annotated training data. The recently…

Semi-supervised domain adaptation (SSDA) aims to adapt models trained from a labeled source domain to a different but related target domain, from which unlabeled data and a small set of labeled data are provided. Current methods that treat…

While unsupervised domain adaptation has been explored to leverage the knowledge from a labeled source domain to an unlabeled target domain, existing methods focus on the distribution alignment between two domains. However, how to better…

Standard segmentation of medical images based on full-supervised convolutional networks demands accurate dense annotations. Such learning framework is built on laborious manual annotation with restrict demands for expertise, leading to…

For monocular depth estimation, acquiring ground truths for real data is not easy, and thus domain adaptation methods are commonly adopted using the supervised synthetic data. However, this may still incur a large domain gap due to the lack…

One of the primary challenges in Semi-supervised Domain Adaptation (SSDA) is the skewed ratio between the number of labeled source and target samples, causing the model to be biased towards the source domain. Recent works in SSDA show that…

The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, the sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are…

Accurate 3D geometry acquisition is essential for a wide range of applications, such as computer graphics, autonomous driving, robotics, and augmented reality. However, raw point clouds acquired in real-world environments are often…

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and…

As the development of 3D sensors, registration of 3D data (e.g. point cloud) coming from different kind of sensor is dispensable and shows great demanding. However, point cloud registration between different sensors is challenging because…

Due to the high annotation cost of large-scale facial landmark detection tasks in videos, a semi-supervised paradigm that uses self-training for mining high-quality pseudo-labels to participate in training has been proposed by researchers.…