Related papers: Mutual Information Guided Backdoor Mitigation for …

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small models. In this study, we…

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can then be used as a feature extractor to build downstream…

Classifiers in supervised learning have various security and privacy issues, e.g., 1) data poisoning attacks, backdoor attacks, and adversarial examples on the security side as well as 2) inference attacks and the right to be forgotten for…

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adversarial attacks,…

Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data. However, previous studies have revealed that such models are vulnerable to backdoor…

Dataset distillation (DD) generates small synthetic datasets that can efficiently train deep networks with a limited amount of memory and compute. Despite the success of DD methods for supervised learning, DD for self-supervised…

Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feature representations from unannotated data. Predominantly used random masking methods make SSL less effective for medical images…

Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world…

Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior…

As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to eliminating the need for labeled data, research has found…

Self-supervised learning (SSL) is now a serious competitor for supervised learning, even though it does not require data annotation. Several baselines have attempted to make SSL models exploit information about data distribution, and less…

Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can be used as backbone…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Multi-Teacher knowledge distillation provides students with additional supervision from multiple pre-trained teachers with diverse information sources. Most existing methods explore different weighting strategies to obtain a powerful…

Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen…

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Semi-supervised machine learning (SSL) is gaining popularity as it reduces the cost of training ML models. It does so by using very small amounts of (expensive, well-inspected) labeled data and large amounts of (cheap, non-inspected)…

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…

Self-supervised learning (SSL) has gained widespread attention in the remote sensing (RS) and earth observation (EO) communities owing to its ability to learn task-agnostic representations without human-annotated labels. Nevertheless, most…