相关论文: Two Independent Teachers are Better Role Model

Training AI models to understand images without costly labeled data remains a challenge. We combine two techniques--DINO (teacher-student learning) and Barlow Twins (redundancy reduction)--to create a model that learns better with fewer…

The online learning of deep neural networks is an interesting problem of machine learning because, for example, major IT companies want to manage the information of the massive data uploaded on the web daily, and this technology can…

The high capacity of deep learning models to learn complex patterns poses a significant challenge when confronted with label noise. The inability to differentiate clean and noisy labels ultimately results in poor generalization. We approach…

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or…

The teacher-student framework, prevalent in semi-supervised semantic segmentation, mainly employs the exponential moving average (EMA) to update a single teacher's weights based on the student's. However, EMA updates raise a problem in that…

Residual network (ResNet) and densely connected network (DenseNet) have significantly improved the training efficiency and performance of deep convolutional neural networks (DCNNs) mainly for object classification tasks. In this paper, we…

We present Token-UNet, adopting the TokenLearner and TokenFuser modules to encase Transformers into UNets. While Transformers have enabled global interactions among input elements in medical imaging, current computational challenges hinder…

We propose self-teaching networks to improve the generalization capacity of deep neural networks. The idea is to generate soft supervision labels using the output layer for training the lower layers of the network. During the network…

Researchers often treat data-driven and theory-driven models as two disparate or even conflicting methods in travel behavior analysis. However, the two methods are highly complementary because data-driven methods are more predictive but…

In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining. However, practical deep classifiers often misidentify these samples, leading to erroneous predictions.…

Deep convolutional neural networks have shown outstanding performance in medical image segmentation tasks. The usual problem when training supervised deep learning methods is the lack of labeled data which is time-consuming and costly to…

Seismic data often contain gaps due to various obstacles in the investigated area and recording instrument failures. Deep learning techniques offer promising solutions for reconstructing missing data parts by leveraging existing…

Deep learning models usually require sufficient training data to achieve high accuracy, but obtaining labeled data can be time-consuming and labor-intensive. Here we introduce a template-based training method to train a 3D U-Net model from…

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate…

Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art results on the Multi-Object Tracking (MOT) benchmarks.…

The segmentation of the pubic symphysis and fetal head (PSFH) constitutes a pivotal step in monitoring labor progression and identifying potential delivery complications. Despite the advances in deep learning, the lack of annotated medical…

Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite for achieving this level of competitiveness is the…

Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which…

Transfer learning enhances the training of novel sensory and decision models by employing rich feature representations from large, pre-trained teacher models. Cognitive neuroscience shows that the human brain creates low-dimensional,…