Related papers: Modulate Your Spectrum in Self-Supervised Learning

Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…

MatSSL is a streamlined self-supervised learning (SSL) architecture that employs Gated Feature Fusion at each stage of the backbone to integrate multi-level representations effectively. Current micrograph analysis of metallic materials…

Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilising prior online…

Large-scale multimodal contrastive learning has recently achieved impressive success in learning rich and transferable representations, yet it remains fundamentally limited by the uniform treatment of feature dimensions and the neglect of…

Semantic segmentation of various tissue and nuclei types in histology images is fundamental to many downstream tasks in the area of computational pathology (CPath). In recent years, Deep Learning (DL) methods have been shown to perform well…

Self-supervised learning (SSL) is recognized as an essential tool for building foundation models for Artificial Intelligence applications. The advances in SSL have been made thanks to vigorous arguments about the principles of SSL and…

Self-supervised learning (SSL) typically learns representations invariant to semantic-preserving augmentations. While effective for recognition, enforcing strong invariance can suppress transformation-dependent structure that is useful for…

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…

Sign language translation (SLT) is typically trained with text in a single spoken language, which limits scalability and cross-language generalization. Earlier approaches have replaced gloss supervision with text-based sentence embeddings,…

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…

Self-supervised learning (SSL) learns knowledge from a large amount of unlabeled data, and then transfers the knowledge to a specific problem with a limited number of labeled data. SSL has achieved promising results in various domains. This…

Inverse rendering is the problem of decomposing an image into its intrinsic components, i.e. albedo, normal and lighting. To solve this ill-posed problem from single image, state-of-the-art methods in shape from shading mostly resort to…

Self-supervised learning is emerging in fine-grained visual recognition with promising results. However, existing self-supervised learning methods are often susceptible to irrelevant patterns in self-supervised tasks and lack the capability…

Ensuring robustness in image watermarking is crucial for and maintaining content integrity under diverse transformations. Recent self-supervised learning (SSL) approaches, such as DINO, have been leveraged for watermarking but primarily…

Non-contrastive SSL methods like BYOL and SimSiam rely on asymmetric predictor networks to avoid representational collapse without negative samples. Yet, how predictor networks facilitate stable learning is not fully understood. While…

Self-supervised learning (SSL) has achieved remarkable performance in pretraining the models that can be further used in downstream tasks via fine-tuning. However, these self-supervised models may not capture meaningful semantic information…

Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that…

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure for the subsequent HSI applications. Unfortunately, though witnessing the development of deep learning in HSI denoising area, existing convolution-based methods face…

Recent algorithms for image manipulation detection almost exclusively use deep network models. These approaches require either dense pixelwise groundtruth masks, camera ids, or image metadata to train the networks. On one hand, constructing…

Recently, self-supervised learning (SSL) methods have been used in pre-training the segmentation models for 2D and 3D medical images. Most of these methods are based on reconstruction, contrastive learning and consistency regularization.…