Related papers: SimTriplet: Simple Triplet Representation Learning…

Deep learning models, e.g. supervised Encoder-Decoder style networks, exhibit promising performance in medical image segmentation, but come with a high labelling cost. We propose TriSegNet, a semi-supervised semantic segmentation framework.…

Graph Self-Supervised Learning (GSSL) has emerged as a powerful paradigm for generating high-quality representations for graph-structured data. While multi-scale graph contrastive learning has received increasing attention, many existing…

Pioneering dual-encoder pre-training works (e.g., CLIP and ALIGN) have revealed the potential of aligning multi-modal representations with contrastive learning. However, these works require a tremendous amount of data and computational…

Most parallel neural network training methods assume homogeneous computing resources. For example, synchronous data-parallel SGD suffers from significant synchronization overhead under heterogeneous workloads, often forcing practitioners to…

3D Gaussian Splatting (3DGS) has emerged as a preferred choice alongside Neural Radiance Fields (NeRF) in inverse rendering due to its superior rendering speed. Currently, the common approach in 3DGS is to utilize "single-view" mini-batch…

In computational pathology, we often face a scarcity of annotations and a large amount of unlabeled data. One method for dealing with this is semi-supervised learning which is commonly split into a self-supervised pretext task and a…

Assume you encounter an inverse problem that shall be solved for a large number of data, but no ground-truth data is available. To emulate this encounter, in this study, we assume it is unknown how to solve the imaging problem of Computed…

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…

Recent progress in Medical Artificial Intelligence (AI) has delivered systems that can reach clinical expert level performance. However, such systems tend to demonstrate sub-optimal "out-of-distribution" performance when evaluated in…

Autonomous driving has attracted much attention over the years but turns out to be harder than expected, probably due to the difficulty of labeled data collection for model training. Self-supervised learning (SSL), which leverages unlabeled…

Contrastive language-image Pre-training (CLIP) [13] can leverage large datasets of unlabeled Image-Text pairs, which have demonstrated impressive performance in various downstream tasks. Given that annotating medical data is time-consuming…

Integration of edge, cloud and space devices into a unified 3D continuum imposes significant challenges for client selection in federated learning systems. Traditional approaches rely on continuous monitoring and historical data collection,…

We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features. CARP learns prototypes in an end-to-end online fashion using gradient descent…

Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appearance to 3D properties…

3D Gaussian Splatting has demonstrated notable success in large-scale scene reconstruction, but challenges persist due to high training memory consumption and storage overhead. Hybrid representations that integrate implicit and explicit…

Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The augmentation enables contrast with another view of a single…

Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. However, most previous works assumed that each view is complete and aligned. This leads to an inevitable deterioration in…

We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly…

Vision Transformers (ViTs) have established new performance benchmarks in vision tasks such as image recognition and object detection. However, these advancements come with significant demands for memory and computational resources,…

Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of…