Related papers: Toward a Geometrical Understanding of Self-supervi…
Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to many factors, especially the nature of the target task. In…
In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use…
Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations. Although SSL has recently reached a milestone: outperforming supervised methods in many modalities\dots…
Linear probing (LP) (and $k$-NN) on the upstream dataset with labels (e.g., ImageNet) and transfer learning (TL) to various downstream datasets are commonly employed to evaluate the quality of visual representations learned via…
Advances in deep learning are re-defining how visual data is processed and understand by the machines. Vision Transformers (ViTs) have recently demonstrated prominent performance in computer vision related tasks. However, their performance…
Recent analyses of self-supervised learning (SSL) find the following data-centric properties to be critical for learning good representations: invariance to task-irrelevant semantics, separability of classes in some latent space, and…
Contrastive learning has been a leading paradigm for self-supervised learning, but it is widely observed that it comes at the price of sacrificing useful features (\eg colors) by being invariant to data augmentations. Given this limitation,…
We propose a novel theoretical framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks (e.g., SimCLR). First, we prove that in each SGD update of SimCLR with various loss…
Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios. Nevertheless, when facing the long-tailed distribution in real-world…
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance. However, the process of collecting and labeling such data can be expensive and time-consuming. Self-supervised…
Self-supervised learning (SSL) approaches have shown promising capabilities in learning the representation from unlabeled data. Amongst them, momentum-based frameworks have attracted significant attention. Despite being a great success,…
Self-supervised Learning (SSL) is a machine learning algorithm for pretraining Deep Neural Networks (DNNs) without requiring manually labeled data. The central idea of this learning technique is based on an auxiliary stage aka pretext task…
Self-supervised learning (SSL) is an emerging paradigm that exploits supervisory signals generated from the data itself, and many recent studies have leveraged SSL to conduct graph anomaly detection. However, we empirically found that three…
Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark…
Recent advancements in self-supervised learning (SSL) made it possible to learn generalizable visual representations from unlabeled data. The performance of Deep Learning models fine-tuned on pretrained SSL representations is on par with…
Unsupervised and self-supervised representation learning has become popular in recent years for learning useful features from unlabelled data. Representation learning has been mostly developed in the neural network literature, and other…
Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects. Although the dense features extracted by employing segmentation maps and bounding…
How do speech models trained through self-supervised learning structure their representations? Previous studies have looked at how information is encoded in feature vectors across different layers. But few studies have considered whether…
An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…
Majority of the current dimensionality reduction or retrieval techniques rely on embedding the learned feature representations onto a computable metric space. Once the learned features are mapped, a distance metric aids the bridging of gaps…