Related papers: Denoising and Selecting Pseudo-Heatmaps for Semi-S…

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliablility of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an…

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lower-bounded by…

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…

Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. However, pseudo-labeling-based semi-supervised approaches suffer from two problems in image classification: (1) Existing methods…

A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…

Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain. To alleviate this reliance, and boost results, semi-supervised approaches…

Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…

Classification predicts classes of objects using the knowledge learned during the training phase. This process requires learning from labeled samples. However, the labeled samples usually limited. Annotation process is annoying, tedious,…

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually…

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they…

The amount of manually labeled data is limited in medical applications, so semi-supervised learning and automatic labeling strategies can be an asset for training deep neural networks. However, the quality of the automatically generated…

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…

In general, human pose estimation methods are categorized into two approaches according to their architectures: regression (i.e., heatmap-free) and heatmap-based methods. The former one directly estimates precise coordinates of each…

To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new…

In semi-supervised learning, the prevailing understanding suggests that observing additional unlabeled samples improves estimation accuracy for linear parameters only in the case of model misspecification. In this work, we challenge such a…

Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D object detection methods directly follow the practice of…

Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy is of great practical significance, because for many…

The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world scenarios, fully…

We study the problem of estimating 3D shape and pose of an object in terms of keypoints, from a single 2D image. The shape and pose are learned directly from images collected by categories and their partial 2D keypoint annotations.. In this…

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…