Add to ORKG11 pages, 17 figures, 5 tablesIn this paper, we introduce a novel method to pseudo-label unlabelled images and train an Auto-Encoder to classify them in a self-supervised manner that allows for a high accuracy and consistency across several datasets. The proposed method consists of first applying a randomly sampled set of data augmentation transformations to each training image. As a result, each initial image can be considered as a pseudo-label to its corresponding augmented ones. Then, an Auto-Encoder is used to learn the mapping between each set of the augmented images and its corresponding pseudo-label. Furthermore, the perceptual loss is employed to take into consideration the existing dependencies between the pixels in the same neighb...
The key to semi-supervised learning (SSL) is to explore adequate information to leverage the unlabel...
The generally unsupervised nature of autoencoder models implies that the main training metric is for...
One of the largest problems in medical image processing is the lack of annotated data. Labeling medi...
In this paper, we propose a novel transductive pseudo-labeling based method for deep semi-supervised...
In this paper we revisit the idea of pseudo-labeling in the context of semi-supervised learning wher...
State-of-the-art computer vision models are mostly trained with supervised learning using human-labe...
While deep learning strategies achieve outstanding results in computer vision tasks, one issue remai...
Abstract—Label noise is not uncommon in machine learning applications nowadays and imposes great cha...
Although deep learning algorithms have achieved significant progress in a variety of domains, they r...
In general, large-scale annotated data are essential to training deep neural networks in order to ac...
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active res...
The auto-encoder model plays a crucial role in the success of deep learning. During the pre-training...
We propose the simple and efficient method of semi-supervised learning for deep neural networks. Bas...
A large part of the current success of deep learning lies in the effectiveness of data -- more preci...
Self-supervised vision transformers (SSTs) have shown great potential to yield rich localization map...
The key to semi-supervised learning (SSL) is to explore adequate information to leverage the unlabel...
The generally unsupervised nature of autoencoder models implies that the main training metric is for...
One of the largest problems in medical image processing is the lack of annotated data. Labeling medi...
In this paper, we propose a novel transductive pseudo-labeling based method for deep semi-supervised...
In this paper we revisit the idea of pseudo-labeling in the context of semi-supervised learning wher...
State-of-the-art computer vision models are mostly trained with supervised learning using human-labe...
While deep learning strategies achieve outstanding results in computer vision tasks, one issue remai...
Abstract—Label noise is not uncommon in machine learning applications nowadays and imposes great cha...
Although deep learning algorithms have achieved significant progress in a variety of domains, they r...
In general, large-scale annotated data are essential to training deep neural networks in order to ac...
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active res...
The auto-encoder model plays a crucial role in the success of deep learning. During the pre-training...
We propose the simple and efficient method of semi-supervised learning for deep neural networks. Bas...
A large part of the current success of deep learning lies in the effectiveness of data -- more preci...
Self-supervised vision transformers (SSTs) have shown great potential to yield rich localization map...
The key to semi-supervised learning (SSL) is to explore adequate information to leverage the unlabel...
The generally unsupervised nature of autoencoder models implies that the main training metric is for...
One of the largest problems in medical image processing is the lack of annotated data. Labeling medi...