Related papers: HoVer-UNet: Accelerating HoVerNet with UNet-based …

Efficient models for remote sensing object counting are urgently required for applications in scenarios with limited computing resources, such as drones or embedded systems. A straightforward yet powerful technique to achieve this is…

Nuclei segmentation is a fundamental but challenging task in the quantitative analysis of histopathology images. Although fully-supervised deep learning-based methods have made significant progress, a large number of labeled images are…

Improving the performance of semantic segmentation models using multispectral information is crucial, especially for environments with low-light and adverse conditions. Multi-modal fusion techniques pursue either the learning of…

Automatic segmentation of diverse heterogeneous brain lesions using multi-modal MRI is a challenging problem in clinical neuroimaging, mainly because of the lack of generalizability and high prediction variance of pathology-specific deep…

Separating overlapped nuclei is a major challenge in histopathology image analysis. Recently published approaches have achieved promising overall performance on nuclei segmentation; however, their performance on separating overlapped nuclei…

In this paper, we explore the redundancy in convolutional neural network, which scales with the complexity of vision tasks. Considering that many front-end visual systems are interested in only a limited range of visual targets, the…

Ensembling is a universally useful approach to boost the performance of machine learning models. However, individual models in an ensemble were traditionally trained independently in separate stages without information access about the…

Agriculture is vital for global food security, but crops are vulnerable to diseases that impact yield and quality. While Convolutional Neural Networks (CNNs) accurately classify plant diseases using leaf images, their high computational…

Medical images are often acquired in different settings, requiring harmonization to adapt to the operating point of algorithms. Specifically, to standardize the physical spacing of imaging voxels in heterogeneous inference settings, images…

This paper presents a study on improving human action recognition through the utilization of knowledge distillation, and the combination of CNN and ViT models. The research aims to enhance the performance and efficiency of smaller student…

Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may…

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional…

A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions. Unfortunately, making predictions using a whole ensemble of…

With the development of deep convolutional neural networks, medical image segmentation has achieved a series of breakthroughs in recent years. However, the high-performance convolutional neural networks always mean numerous parameters and…

Recent recommender systems have shown remarkable performance by using an ensemble of heterogeneous models. However, it is exceedingly costly because it requires resources and inference latency proportional to the number of models, which…

Multi-scenario & multi-task learning has been widely applied to many recommendation systems in industrial applications, wherein an effective and practical approach is to carry out multi-scenario transfer learning on the basis of the…

Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student neural network. Existing knowledge transfer approaches match…

The recent 3D medical ViTs (e.g., SwinUNETR) achieve the state-of-the-art performances on several 3D volumetric data benchmarks, including 3D medical image segmentation. Hierarchical transformers (e.g., Swin Transformers) reintroduced…

It is a challenging task to accurately perform semantic segmentation due to the complexity of real picture scenes. Many semantic segmentation methods based on traditional deep learning insufficiently captured the semantic and appearance…

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…