Related papers: Temporal coherence-based self-supervised learning …

Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee…

We introduce a novel self-supervised contrastive learning method to learn representations from unlabelled videos. Existing approaches ignore the specifics of input distortions, e.g., by learning invariance to temporal transformations.…

In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale image classification…

Deep neural networks require collecting and annotating large amounts of data to train successfully. In order to alleviate the annotation bottleneck, we propose a novel self-supervised representation learning approach for spatiotemporal…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long…

Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training. Most prior work has done so by increasing pre-training computation by adding complex…

Convolutional neural networks trained without supervision come close to matching performance with supervised pre-training, but sometimes at the cost of an even higher number of parameters. Extracting subnetworks from these large…

We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it…

Pre-training on time series poses a unique challenge due to the potential mismatch between pre-training and target domains, such as shifts in temporal dynamics, fast-evolving trends, and long-range and short-cyclic effects, which can lead…

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…

In recent years, graph neural networks (GNNs) have been widely adopted in the representation learning of graph-structured data and provided state-of-the-art performance in various applications such as link prediction, node classification,…

Given the difficulty of manually annotating motion in video, the current best motion estimation methods are trained with synthetic data, and therefore struggle somewhat due to a train/test gap. Self-supervised methods hold the promise of…

A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…

Video super-resolution (VSR) is a task that aims to reconstruct high-resolution (HR) frames from the low-resolution (LR) reference frame and multiple neighboring frames. The vital operation is to utilize the relative misaligned frames for…

Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data structure or context by solving a pretext task.…

How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact…

We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task, while exploiting both frame-level and video-level information. We leverage a novel combination of temporal alignment…

Unsupervised pre-training was a critical technique for training deep neural networks years ago. With sufficient labeled data and modern training techniques, it is possible to train very deep neural networks from scratch in a purely…

Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the…