Related papers: Transferability of Representations Learned using S…

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets.…

Traditional supervised learning methods are hitting a bottleneck because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks. A…

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a…

Radio Frequency (RF) device fingerprinting has been recognized as a potential technology for enabling automated wireless device identification and classification. However, it faces a key challenge due to the domain shift that could arise…

Understanding what information neural networks capture is an essential problem in deep learning, and studying whether different models capture similar features is an initial step to achieve this goal. Previous works sought to define metrics…

Self-supervised learning in computer vision aims to leverage the inherent structure and relationships within data to learn meaningful representations without explicit human annotation, enabling a holistic understanding of visual scenes.…

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has…

Contrastive visual pretraining based on the instance discrimination pretext task has made significant progress. Notably, recent work on unsupervised pretraining has shown to surpass the supervised counterpart for finetuning downstream…

Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has…

In recent years, contrastive learning achieves impressive results on self-supervised visual representation learning, but there still lacks a rigorous understanding of its learning dynamics. In this paper, we show that if we cast a…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observations (e.g., images), a line of approaches use deep learning to…

Self-supervised learning (SSL) learns high-quality representations from large pools of unlabeled training data. As datasets grow larger, it becomes crucial to identify the examples that contribute the most to learning such representations.…

Deep learning has transformed computer vision but relies heavily on large labeled datasets and computational resources. Transfer learning, particularly fine-tuning pretrained models, offers a practical alternative; however, models…

Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data…

Recent advancements in contrastive learning have revolutionized self-supervised representation learning and achieved state-of-the-art performance on benchmark tasks. While most existing methods focus on applying contrastive learning to…

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…

Although deep convolutional networks have achieved great performance in face recognition tasks, the challenge of domain discrepancy still exists in real world applications. Lack of domain coverage of training data (source domain) makes the…

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…

Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different…