Related papers: JEPAMatch: Geometric Representation Shaping for Se…
Ultrasound (US) imaging poses unique challenges for representation learning due to its inherently noisy acquisition process. The low signal-to-noise ratio and stochastic speckle patterns hinder standard self-supervised learning methods…
Semi-supervised semantic segmentation aims to utilize limited labeled images and abundant unlabeled images to achieve label-efficient learning, wherein the weak-to-strong consistency regularization framework, popularized by FixMatch, is…
Learning manipulable representations of the world and its dynamics is central to AI. Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of practical guidance and theory has led to ad-hoc R&D. We present a…
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of…
Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-based model by predicting the latent representation of a…
This paper tackles the problem of semi-supervised learning when the set of labeled samples is limited to a small number of images per class, typically less than 10, problem that we refer to as barely-supervised learning. We analyze in depth…
Pseudo-labeling is a crucial technique in semi-supervised learning (SSL), where artificial labels are generated for unlabeled data by a trained model, allowing for the simultaneous training of labeled and unlabeled data in a supervised…
Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…
Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their…
Joint Embedding Predictive Architectures (JEPA) have emerged as a powerful framework for learning general-purpose representations. However, these models often lack interpretability and suffer from inefficiencies due to dense embedding…
This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative…
Self-supervised learning has seen great success recently in unsupervised representation learning, enabling breakthroughs in natural language and image processing. However, these methods often rely on autoregressive and masked modeling,…
Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of mitigating the dependence on large labeled datasets. The latest methods (e.g., FixMatch) use a combination of consistency regularization and…
Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for learning transferable features. In particular, Image-based Joint-Embedding Predictive…
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization…
We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance. Most existing semi-supervised methods rely on the assumption that…
We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label,…
Surgical instrument segmentation is recognised as a key enabler in providing advanced surgical assistance and improving computer-assisted interventions. In this work, we propose SegMatch, a semi-supervised learning method to reduce the need…
In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…
Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…