Related papers: CLExtract: Recovering Highly Corrupted DVB/GSE Sat…

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets.…

Semi-supervised learning (SSL) algorithms have had great success in recent years in limited labeled data regimes. However, the current state-of-the-art SSL algorithms are computationally expensive and entail significant compute time and…

Weather data, comprising multiple variables, poses significant challenges due to its high dimensionality and multimodal nature. Creating low-dimensional embeddings requires compressing this data into a compact, shared latent space. This…

Global Navigation Satellite System (GNSS) signals are fundamental in applications across navigation, transportation, and industrial networks. However, their extremely low received power makes them highly vulnerable to radio-frequency…

Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

Contrastive steering has been shown as a simple and effective method to adjust the generative behavior of LLMs at inference time. It uses examples of prompt responses with and without a trait to identify a direction in an intermediate…

Time series forecasting (TSF) holds significant importance in modern society, spanning numerous domains. Previous representation learning-based TSF algorithms typically embrace a contrastive learning paradigm featuring segregated…

Chromosome recognition is an essential task in karyotyping, which plays a vital role in birth defect diagnosis and biomedical research. However, existing classification methods face significant challenges due to the inter-class similarity…

State-of-the-art object detection methods applied to satellite and drone imagery largely fail to identify small and dense objects. One reason is the high variability of content in the overhead imagery due to the terrestrial region captured…

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…

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…

We present a self-supervised approach for characterizing low surface brightness tidal features in wide-field imaging data by applying the nearest-neighbor contrastive learning of visual representations (NNCLR) algorithm to a curated subset…

Learning node-level representations of heterophilic graphs is crucial for various applications, including fraudster detection and protein function prediction. In such graphs, nodes share structural similarity identified by the equivalence…

Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…

Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in…

Self-supervised learning (SSL) has emerged as a powerful approach to learning representations, particularly in the field of computer vision. However, its application to dependent data, such as temporal and spatio-temporal domains, remains…

We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on clean images, like CLIP. The problem is to recover the…

Graph contrastive learning algorithms have demonstrated remarkable success in various applications such as node classification, link prediction, and graph clustering. However, in unsupervised graph contrastive learning, some contrastive…

Graph contrastive learning (GCL) has become a powerful tool for learning graph data, but its scalability remains a significant challenge. In this work, we propose a simple yet effective training framework called Structural Compression…