Related papers: Self-supervised Pretraining of Visual Features in …
Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a 'pretext task' that does not require ground-truth labels/annotation. This…
Consistency training, which exploits both supervised and unsupervised learning with different augmentations on image, is an effective method of utilizing unlabeled data in semi-supervised learning (SSL) manner. Here, we present another…
The process of annotating relevant data in the field of digital microscopy can be both time-consuming and especially expensive due to the required technical skills and human-expert knowledge. Consequently, large amounts of microscopic image…
Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…
Convolutional neural networks perform well on object recognition because of a number of recent advances: rectified linear units (ReLUs), data augmentation, dropout, and large labelled datasets. Unsupervised data has been proposed as another…
Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…
Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabilities of these algorithms in scenarios where such input is…
We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to…
In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this…
Unsupervised lifelong learning refers to the ability to learn over time while memorizing previous patterns without supervision. Although great progress has been made in this direction, existing work often assumes strong prior knowledge…
Deep Learning has led to a dramatic leap in Super-Resolution (SR) performance in the past few years. However, being supervised, these SR methods are restricted to specific training data, where the acquisition of the low-resolution (LR)…
Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…
Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful…
Recent research put a big effort in the development of deep learning architectures and optimizers obtaining impressive results in areas ranging from vision to language processing. However little attention has been addressed to the need of a…
Recent advances have spurred incredible progress in self-supervised pretraining for vision. We investigate what factors may play a role in the utility of these pretraining methods for practitioners. To do this, we evaluate various…
Assuming a known degradation model, the performance of a learned image super-resolution (SR) model depends on how well the variety of image characteristics within the training set matches those in the test set. As a result, the performance…
Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on deep learning and thus require vast amounts of training data. Due to their scarcity and minuscule size,…
A prominent approach to visual Reinforcement Learning (RL) is to learn an internal state representation using self-supervised methods, which has the potential benefit of improved sample-efficiency and generalization through additional…
Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification. This dependence on…
Semi-supervised algorithms aim to learn prediction functions from a small set of labeled observations and a large set of unlabeled observations. Because this framework is relevant in many applications, they have received a lot of interest…