Related papers: PLAD: Learning to Infer Shape Programs with Pseudo…
Supervised-learning based person re-identification (re-id) require a large amount of manual labeled data, which is not applicable in practical re-id deployment. In this work, we propose a Support Pair Active Learning (SPAL) framework to…
A common classification task situation is where one has a large amount of data available for training, but only a small portion is annotated with class labels. The goal of semi-supervised training, in this context, is to improve…
Semi-supervised medical image segmentation has gained growing interest due to its ability to utilize unannotated data. The current state-of-the-art methods mostly rely on pseudo-labeling within a co-training framework. These methods depend…
Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach involves training an image classification network using global…
Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…
We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model. Key to our approach are a strong baseline acoustic and…
The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to…
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…
The proliferation of extensive neural network architectures, particularly deep learning models, presents a challenge in terms of resource-intensive training. GPU memory constraints have become a notable bottleneck in training such sizable…
Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus,…
While fine-tuning pre-trained networks has become a popular way to train image segmentation models, such backbone networks for image segmentation are frequently pre-trained using image classification source datasets, e.g., ImageNet. Though…
Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a…
Semi-supervised multi-label learning (SSMLL) aims to address the challenge of limited labeled data in multi-label learning (MLL) by leveraging unlabeled data to improve the model's performance. While pseudo-labeling has become a dominant…
Training neural networks to perform 3D object detection for autonomous driving requires a large amount of diverse annotated data. However, obtaining training data with sufficient quality and quantity is expensive and sometimes impossible…
Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for labelling large number of images, the amount of available training data is always limited. To produce more data…
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…
Unsupervised Domain Adaptive Object Detection (UDA-OD) uses unlabelled data to improve the reliability of robotic vision systems in open-world environments. Previous approaches to UDA-OD based on self-training have been effective in…
Witnessing the success of deep learning neural networks in natural image processing, an increasing number of studies have been proposed to develop deep-learning-based frameworks for medical image segmentation. However, since the pixel-wise…
Identifying anomalous instances in tabular data is essential for improving data reliability and maintaining system stability. Due to the scarcity of ground-truth anomaly labels, existing methods mainly rely on unsupervised anomaly detection…
Like humans, deep networks have been shown to learn better when samples are organized and introduced in a meaningful order or curriculum. Conventional curriculum learning schemes introduce samples in their order of difficulty. This forces…