Related papers: Geometry-Aware Contrastive Learning for Few-Shot A…

Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The…

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Deep neural networks have been widely studied in autonomous driving applications such as semantic segmentation or depth estimation. However, training a neural network in a supervised manner requires a large amount of annotated labels which…

Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the…

Recently, deep end-to-end learning has been studied for intent classification in Spoken Language Understanding (SLU). However, end-to-end models require a large amount of speech data with intent labels, and highly optimized models are…

Conventional Graph Contrastive Learning (GCL) on Text-Attributed Graphs (TAGs) relies on blind stochastic augmentations, inadvertently entangling task-relevant signals with noise. We propose SDM-SCR, a robust framework anchored in…

Self-supervised learning (SSL) is a method that learns the data representation by utilizing supervision inherent in the data. This learning method is in the spotlight in the drug field, lacking annotated data due to time-consuming and…

Human action recognition (HAR) with multi-modal inputs (RGB-D, skeleton, point cloud) can achieve high accuracy but typically relies on large labeled datasets and degrades sharply when sensors fail or are noisy. We present Robust…

Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches.…

Hyperspectral images with high spectral resolution provide new insights into recognizing subtle differences in similar substances. However, object detection in hyperspectral images faces significant challenges in intra- and inter-class…

Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To…

One-stage object detectors such as the YOLO family achieve state-of-the-art performance in real-time vision applications but remain heavily reliant on large-scale labeled datasets for training. In this work, we present a systematic study of…

In this paper, we introduce a novel method designed to enhance label efficiency in satellite imagery analysis by integrating semi-supervised learning (SSL) with active learning strategies. Our approach utilizes contrastive learning together…

Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings. Meanwhile, the time-consuming and costly process of annotating graph labels manually…

Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing the Image-augmentation based Prediction consistency and…

Recent advances in neural radiation fields (NeRF) and 3D Gaussian-based SLAM have achieved impressive localization accuracy and high-quality dense mapping in static scenes. However, these methods remain challenged in dynamic environments,…

While self-supervised representation learning (SSL) has received widespread attention from the community, recent research argue that its performance will suffer a cliff fall when the model size decreases. The current method mainly relies on…

Most recent self-supervised learning methods learn visual representation by contrasting different augmented views of images. Compared with supervised learning, more aggressive augmentations have been introduced to further improve the…

3D-aware Generative Adversarial Networks (3D-GANs) currently exhibit artifacts in their 3D geometrical modeling, such as mesh imperfections and holes. These shortcomings are primarily attributed to the limited availability of annotated 3D…

Contrastive learning has been proven beneficial for self-supervised skeleton-based action recognition. Most contrastive learning methods utilize carefully designed augmentations to generate different movement patterns of skeletons for the…