相关论文: Unsupervised Local Plasticity in a Multi-Frequency…

Deep neural networks trained on biased data often inadvertently learn unintended inference rules, particularly when labels are strongly correlated with biased features. Existing bias mitigation methods typically involve either a)…

State-of-the-art computer vision models are mostly trained with supervised learning using human-labeled images, which limits their scalability due to the expensive annotation cost. While self-supervised representation learning has achieved…

We are interested in representation learning from labeled or unlabeled data. Inspired by recent success of self-supervised learning (SSL), we develop a non-contrastive representation learning method that can exploit additional knowledge.…

This paper presents a study of semi-supervised learning with large convolutional networks. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images (up to 1 billion). Our main goal…

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually…

In machine learning, error back-propagation in multi-layer neural networks (deep learning) has been impressively successful in supervised and reinforcement learning tasks. As a model for learning in the brain, however, deep learning has…

Despite recent progress made by self-supervised methods in representation learning with residual networks, they still underperform supervised learning on the ImageNet classification benchmark, limiting their applicability in…

Reducing the amount of labels required to train convolutional neural networks without performance degradation is key to effectively reduce human annotation efforts. We propose Reliable Label Bootstrapping (ReLaB), an unsupervised…

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…

Upon deployment to edge devices, it is often desirable for a model to further learn from streaming data to improve accuracy. However, extracting representative features from such data is challenging because it is typically unlabeled,…

We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly…

Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs).…

Machine learning and deep learning have shown great promise in mobile sensing applications, including Human Activity Recognition. However, the performance of such models in real-world settings largely depends on the availability of large…

Plastic self-adaptation, nonlinear recurrent dynamics and multi-scale memory are desired features in hardware implementations of neural networks, because they enable them to learn, adapt and process information similarly to the way…

Rapidly learning from ongoing experiences and remembering past events with a flexible memory system are two core capacities of biological intelligence. While the underlying neural mechanisms are not fully understood, various evidence…

Unsupervised learning of hierarchical representations has been one of the most vibrant research directions in deep learning during recent years. In this work we study biologically inspired unsupervised strategies in neural networks based on…

We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings:…

Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of expensive annotations,…

We consider the problem of building high-level, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally…

Semi-supervised learning aims to train a model using limited labels. State-of-the-art semi-supervised methods for image classification such as PAWS rely on self-supervised representations learned with large-scale unlabeled but curated data.…