Related papers: Expressive yet Efficient Feature Expansion with Ad…
Achieving high-quality High Dynamic Range (HDR) imaging on resource-constrained edge devices is a critical challenge in computer vision, as its performance directly impacts downstream tasks such as intelligent surveillance and autonomous…
Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant…
Deep neural networks (DNN) have shown unprecedented success in various computer vision applications such as image classification and object detection. However, it is still a common annoyance during the training phase, that one has to…
Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…
Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and large deformations, often resulting in suboptimal accuracy. Robustness to these challenges can be…
Current anomaly detection methods primarily focus on low-resolution scenarios. For high-resolution images, conventional downsampling often results in missed detections of subtle anomalous regions due to the loss of fine-grained…
Deep learning-based diagnostic models often suffer performance drops due to distribution shifts between training (source) and test (target) domains. Collecting and labeling sufficient target domain data for model retraining represents an…
Image classification is one of the most fundamental tasks in Computer Vision. In practical applications, the datasets are usually not as abundant as those in the laboratory and simulation, which is always called as Data Hungry. How to…
In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly…
3D Anomaly Detection (AD) has shown great potential in detecting anomalies or defects of high-precision industrial products. However, existing methods are typically trained in a class-specific manner and also lack the capability of learning…
The integration of pathologic images and genomic data for survival analysis has gained increasing attention with advances in multimodal learning. However, current methods often ignore biological characteristics, such as heterogeneity and…
Handwritten Word Recognition and Spotting is a challenging field dealing with handwritten text possessing irregular and complex shapes. The design of deep neural network models makes it necessary to extend training datasets in order to…
Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit suboptimal performance under extreme conditions such as…
Recently, methods based on deep learning have been successfully applied to ship detection for synthetic aperture radar (SAR) images. Despite the development of numerous ship detection methodologies, detecting small and coastal ships remains…
Semantic segmentation in very high resolution (VHR) aerial images is one of the most challenging tasks in remote sensing image understanding. Most of the current approaches are based on deep convolutional neural networks (DCNNs). However,…
Deep neural network inference accelerators are rapidly growing in importance as we turn to massively parallelized processing beyond GPUs and ASICs. The dominant operation in feedforward inference is the multiply-and-accumlate process, where…
Random projections or sketching are widely used in many algorithmic and learning contexts. Here we study the performance of iterative Hessian sketch for least-squares problems. By leveraging and extending recent results from random matrix…
Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…
Mathematical theory shows us that multilayer feedforward Artificial Neural Networks(ANNs) are universal function approximators, capable of approximating any measurable function to any desired degree of accuracy. In practice designing…
Industrial experimentation requires both factor screening to identify critical variables and response optimization to find optimal operating conditions. Traditional approaches treat these as separate phases, necessitating costly sequential…