Related papers: Acceleration of Histogram-Based Contrast Enhanceme…
Neighbour embeddings (NE) allow the representation of high dimensional datasets into lower dimensional spaces and are often used in data visualisation. In practice, accelerated approximations are employed to handle very large datasets.…
Medical image retrieval (MIR) is a critical component of computer-aided diagnosis, yet existing systems suffer from three persistent limitations: uniform feature encoding that fails to account for the varying clinical importance of…
This paper presents a whitening-based contrastive learning method for sentence embedding learning (WhitenedCSE), which combines contrastive learning with a novel shuffled group whitening. Generally, contrastive learning pulls distortions of…
There is a growing interest in custom spatial accelerators for machine learning applications. These accelerators employ a spatial array of processing elements (PEs) interacting via custom buffer hierarchies and networks-on-chip. The…
This paper presents Contrastive Reconstruction, ConRec - a self-supervised learning algorithm that obtains image representations by jointly optimizing a contrastive and a self-reconstruction loss. We showcase that state-of-the-art…
Recent advances in computational pathology have leveraged vision-language models to learn joint representations of Hematoxylin and Eosin (HE) images with spatial transcriptomic (ST) profiles. However, existing approaches typically align HE…
Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two views of an image. NCE uses randomly sampled negative…
In recent years, histopathology images have been increasingly used as a diagnostic tool in the medical field. The process of accurately diagnosing a biopsy sample requires significant expertise in the field, and as such can be…
Dynamic Contrast-enhanced Magnetic Resonance Imaging (DCE-MRI) is an important tool for detecting subtle kinetic changes in cancerous tissue. Quantitative analysis of DCE-MRI typically involves the convolution of an arterial input function…
Bottleneck autoencoders have been actively researched as a solution to image compression tasks. However, we observed that bottleneck autoencoders produce subjectively low quality reconstructed images. In this work, we explore the ability of…
Snapshot compressive imaging (SCI) refers to compressive imaging systems where multiple frames are mapped into a single measurement, with video compressive imaging and hyperspectral compressive imaging as two representative applications.…
We propose a Deep learning-based weak label learning method for analyzing whole slide images (WSIs) of Hematoxylin and Eosin (H&E) stained tumor tissue not requiring pixel-level or tile-level annotations using Self-supervised pre-training…
In convolutional neural networks (CNNs), downsampling operations are crucial to model performance. Although traditional downsampling methods (such as maximum pooling and cross-row convolution) perform well in feature aggregation, receptive…
Ensuring validation for highly automated driving poses significant obstacles to the widespread adoption of highly automated vehicles. Scenario-based testing offers a potential solution by reducing the homologation effort required for these…
Hyperspectral image (HSI) clustering is gaining considerable attention owing to recent methods that overcome the inefficiency and misleading results from the absence of supervised information. Contrastive learning methods excel at existing…
Ensemble clustering integrates a set of base clustering results to generate a stronger one. Existing methods usually rely on a co-association (CA) matrix that measures how many times two samples are grouped into the same cluster according…
Contrastive learning has recently attracted plenty of attention in deep graph clustering for its promising performance. However, complicated data augmentations and time-consuming graph convolutional operation undermine the efficiency of…
Document image binarization is the initial step and a crucial in many document analysis and recognition scheme. In fact, it is still a relevant research subject and a fundamental challenge due to its importance and influence. This paper…
Recent studies have shown that CLIP model's adversarial robustness in zero-shot classification tasks can be enhanced by adversarially fine-tuning its image encoder with adversarial examples (AEs), which are generated by minimizing the…
The outcome of text recognition for degraded color documents is often unsatisfactory due to interference from various contaminants. To extract information more efficiently for text recognition, document image enhancement and binarization…