Related papers: HYperbolic Self-Paced Learning for Self-Supervised…

Most real-world datasets consist of a natural hierarchy between classes or an inherent label structure that is either already available or can be constructed cheaply. However, most existing representation learning methods ignore this…

Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achieve invariant…

Prediction is a fundamental capability of all living organisms, and has been proposed as an objective for learning sensory representations. Recent work demonstrates that in primate visual systems, prediction is facilitated by neural…

Recently, a few self-supervised representation learning (SSL) methods have outperformed the ImageNet classification pre-training for vision tasks such as object detection. However, its effects on 3D human body pose and shape estimation…

This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer. In this work, functional knowledge transfer is achieved by joint optimization of self-supervised…

Brain-inspired machine intelligence research seeks to develop computational models that emulate the information processing and adaptability that distinguishes biological systems of neurons. This has led to the development of spiking neural…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie,…

Self-supervised contrastive learning is an effective approach for addressing the challenge of limited labelled data. This study builds upon the previously established two-stage patch-level, multi-label classification method for…

Remote sensing data has been widely used for various Earth Observation (EO) missions such as land use and cover classification, weather forecasting, agricultural management, and environmental monitoring. Most existing remote sensing…

The self-supervised ultrasound (US) video model pretraining can use a small amount of labeled data to achieve one of the most promising results on US diagnosis. However, it does not take full advantage of multi-level knowledge for learning…

Motions are reflected in videos as the movement of pixels, and actions are essentially patterns of inconsistent motions between the foreground and the background. To well distinguish the actions, especially those with complicated…

Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…

Most semi-supervised skeleton-based action recognition approaches aim to learn the skeleton action representations only at the joint level, but neglect the crucial motion characteristics at the coarser-grained body (e.g., limb, trunk) level…

The cost of head pose labeling is the main challenge of improving the fine-grained Head Pose Estimation (HPE). Although Self-Supervised Learning (SSL) can be a solution to the lack of huge amounts of labeled data, its efficacy for…

Recently, there have been efforts to improve the performance in sign language recognition by designing self-supervised learning methods. However, these methods capture limited information from sign pose data in a frame-wise learning manner,…

Action recognition via 3D skeleton data is an emerging important topic in these years. Most existing methods either extract hand-crafted descriptors or learn action representations by supervised learning paradigms that require massive…

We present a simple picture of the training process of joint embedding self-supervised learning methods. We find that these methods learn their high-dimensional embeddings one dimension at a time in a sequence of discrete, well-separated…

Recent progress in object pose prediction provides a promising path for robots to build object-level scene representations during navigation. However, as we deploy a robot in novel environments, the out-of-distribution data can degrade the…

In recent years, discriminative self-supervised methods have made significant strides in advancing various visual tasks. The central idea of learning a data encoder that is robust to data distortions/augmentations is straightforward yet…

This paper presents a novel holistic deep learning framework that simultaneously addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability from different train-validation splits. The…