Related papers: SMFormer: Empowering Self-supervised Stereo Matchi…
Many leading self-supervised methods for unsupervised representation learning, in particular those for embedding image features, are built on variants of the instance discrimination task, whose optimization is known to be prone to…
In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to…
Blind face restoration aims at recovering high-quality face images from those with unknown degradations. Current algorithms mainly introduce priors to complement high-quality details and achieve impressive progress. However, most of these…
Support vector machine (SVM) is one of the most studied paradigms in the realm of machine learning for classification and regression problems. It relies on vectorized input data. However, a significant portion of the real-world data exists…
Self-supervised visual representation methods are closing the gap with supervised learning performance. These methods rely on maximizing the similarity between embeddings of related synthetic inputs created through data augmentations. This…
Medical imaging provides many valuable clues involving anatomical structure and pathological characteristics. However, image degradation is a common issue in clinical practice, which can adversely impact the observation and diagnosis by…
Direction-of-Arrival (DOA) estimation in sensor arrays faces limitations under demanding conditions, including low signal-to-noise ratio, single-snapshot scenarios, coherent sources, and unknown source counts. Conventional beamforming…
The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different…
Under stereo settings, the problem of image super-resolution (SR) and disparity estimation are interrelated that the result of each problem could help to solve the other. The effective exploitation of correspondence between different views…
Achieving pixel-level registration between SAR and optical images remains a challenging task due to their fundamentally different imaging mechanisms and visual characteristics. Although deep learning has achieved great success in many…
Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various applications. However, in case we have multiple views of…
Supervised and unsupervised homography estimation methods depend on image pairs tailored to specific modalities to achieve high accuracy. However, their performance deteriorates substantially when applied to unseen modalities. To address…
Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…
Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation models have demonstrated promising generalization across EO…
Real-image super-resolution (Real-ISR) seeks to recover HR images from LR inputs with mixed, unknown degradations. While diffusion models surpass GANs in perceptual quality, they under-reconstruct high-frequency (HF) details due to a…
This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantly use real images, MixDiff uses a variant of Stable…
Multimodal Large Language Models (MLLMs) have shown strong potential for radiology report generation, yet their clinical translation is hindered by architectural heterogeneity and the prevalence of factual hallucinations. Standard…
Support Vector Machines (SVMs) are an important tool for performing classification on scattered data, where one usually has to deal with many data points in high-dimensional spaces. We propose solving SVMs in primal form using feature maps…
Many recent semi-supervised learning (SSL) studies build teacher-student architecture and train the student network by the generated supervisory signal from the teacher. Data augmentation strategy plays a significant role in the SSL…
Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…