Related papers: SDAT: Sub-Dataset Alternation Training for Improve…

Single image dehazing is a challenging task, for which the domain shift between synthetic training data and real-world testing images usually leads to degradation of existing methods. To address this issue, we propose a novel image dehazing…

Visual anomaly detection, an important problem in computer vision, is usually formulated as a one-class classification and segmentation task. The student-teacher (S-T) framework has proved to be effective in solving this challenge. However,…

We develop a neural network architecture which, trained in an unsupervised manner as a denoising diffusion model, simultaneously learns to both generate and segment images. Learning is driven entirely by the denoising diffusion objective,…

It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…

Image denoising is a classical problem in low level computer vision. Model-based optimization methods and deep learning approaches have been the two main strategies for solving the problem. Model-based optimization methods are flexible for…

Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the field, many of them still rely on standard loss functions like Cross-Entropy and Dice,…

Structured illumination (SI) enhances image resolution and contrast by projecting patterned light onto a sample. In two-phase optical-sectioning SI (OS-SI), reduced acquisition time introduces residual artifacts that conventional denoising…

Hyperspectral image super-resolution is essential for enhancing the spatial fidelity of HSI data, yet existing deep learning methods often struggle with substantial spectral redundancy and the limited non-linear modeling capacity of…

Deep learning has potential to automate screening, monitoring and grading of disease in medical images. Pretraining with contrastive learning enables models to extract robust and generalisable features from natural image datasets,…

In many modern computer application problems, the classification of image data plays an important role. Among many different supervised machine learning models, convolutional neural networks (CNNs) and linear discriminant analysis (LDA) as…

Building detection from satellite multispectral imagery data is being a fundamental but a challenging problem mainly because it requires correct recovery of building footprints from high-resolution images. In this work, we propose a deep…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Deep convolutional networks often append additive constant ("bias") terms to their convolution operations, enabling a richer repertoire of functional mappings. Biases are also used to facilitate training, by subtracting mean response over…

Image normalization is a building block in medical image analysis. Conventional approaches are customarily utilized on a per-dataset basis. This strategy, however, prevents the current normalization algorithms from fully exploiting the…

Spiking Neural Networks (SNNs) offer a promising alternative to traditional deep learning frameworks, since they provide higher computational efficiency due to event-driven information processing. SNNs distribute the analog values of pixel…

We present a simple and effective pretraining strategy {D}en{o}ising {T}raining DoT for neural machine translation. Specifically, we update the model parameters with source- and target-side denoising tasks at the early stage and then tune…

Spectral imaging technologies have rapidly evolved during the past decades. The recent development of single-camera-one-shot techniques for hyperspectral imaging allows multiple spectral bands to be captured simultaneously (3x3, 4x4 or 5x5…

Attention mechanisms have become of crucial importance in deep learning in recent years. These non-local operations, which are similar to traditional patch-based methods in image processing, complement local convolutions. However, computing…

Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise of reduced computation, DST methods converge significantly slower than dense training,…

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…