Related papers: Discriminative Representation learning via Attenti…
Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses challenges in supervised contrastive learning (SCL), where the…
Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations…
Recently the deep learning has shown its advantage in representation learning and clustering for time series data. Despite the considerable progress, the existing deep time series clustering approaches mostly seek to train the deep neural…
The recent breakthrough achieved by contrastive learning accelerates the pace for deploying unsupervised training on real-world data applications. However, unlabeled data in reality is commonly imbalanced and shows a long-tail distribution,…
Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach…
Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. Existing methods such as data reweighing, resampling, and supervised contrastive learning enforce the class balance…
Appearance-based gaze estimation always suffers from poor generalization due to limited annotated samples and insufficient dataset diversity. Leading approaches adopt weakly supervised learning to generate large-scale pseudo-labeled data…
We present a discriminative clustering approach in which the feature representation can be learned from data and moreover leverage labeled data. Representation learning can give a similarity-based clustering method the ability to…
Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the…
Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The…
Unsupervised out-of-distribution (OOD) Detection aims to separate the samples falling outside the distribution of training data without label information. Among numerous branches, contrastive learning has shown its excellent capability of…
To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…
Graph-level representations are critical in various real-world applications, such as predicting the properties of molecules. But in practice, precise graph annotations are generally very expensive and time-consuming. To address this issue,…
Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…
Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…
We introduce Consistent Assignment for Representation Learning (CARL), an unsupervised learning method to learn visual representations by combining ideas from self-supervised contrastive learning and deep clustering. By viewing contrastive…
Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions. However, the quality of generated pseudo-labels has been a…
Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields. Integrating AT into SSL, multiple prior works have accomplished a…
Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and…
Contrastive self-supervised learning (CSL) based on instance discrimination typically attracts positive samples while repelling negatives to learn representations with pre-defined binary self-supervision. However, vanilla CSL is inadequate…