Related papers: Unsupervised Visual Representation Learning via Mu…
In recent years, self-supervised learning has been studied to deal with the limitation of available labeled-dataset. Among the major components of self-supervised learning, the data augmentation pipeline is one key factor in enhancing the…
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art. Like Pseudo Labels, Meta Pseudo Labels has a…
Pseudo-supervised learning methods have been shown to be effective for weakly supervised object localization tasks. However, the effectiveness depends on the powerful regularization ability of deep neural networks. Based on the assumption…
In this paper, we propose a novel active learning approach integrated with an improved semi-supervised learning framework to reduce the cost of manual annotation and enhance model performance. Our proposed approach effectively leverages…
Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms. However, such clustering-based scheme becomes…
Deep neural networks are capable of learning powerful representations to tackle complex vision tasks but expose undesirable properties like the over-fitting issue. To this end, regularization techniques like image augmentation are necessary…
Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an…
Learning meaningful representations is at the heart of many tasks in the field of modern machine learning. Recently, a lot of methods were introduced that allow learning of image representations without supervision. These representations…
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…
Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…
Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-learning in few-shot…
Person re-identification (re-ID) aims at identifying the same persons' images across different cameras. However, domain diversities between different datasets pose an evident challenge for adapting the re-ID model trained on one dataset to…
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…
Semi-supervised action recognition is a challenging but important task due to the high cost of data annotation. A common approach to this problem is to assign unlabeled data with pseudo-labels, which are then used as additional supervision…
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…
The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains. Self-supervised learning, a paradigm which exploits the structure of unlabeled data to create…
Mutual information maximization provides an appealing formalism for learning representations of data. In the context of reinforcement learning (RL), such representations can accelerate learning by discarding irrelevant and redundant…
Pretext Invariant Representation Learning (PIRL) followed by Supervised Fine-Tuning (SFT) has become a standard paradigm for learning with limited labels. We extend this approach to the Positive Unlabeled (PU) setting, where only a small…
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.…
Labeling data is often very time consuming and expensive, leaving us with a majority of unlabeled data. Self-supervised representation learning methods such as SimCLR (Chen et al., 2020) or BYOL (Grill et al., 2020) have been very…