Related papers: Transformer Compressed Sensing via Global Image To…

Deep Convolutional Neural Networks (CNNs) for image classification successively alternate convolutions and downsampling operations, such as pooling layers or strided convolutions, resulting in lower resolution features the deeper the…

Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID). However, most existing BSNs are conducted with convolution layers. Although transformers have shown the potential to overcome the…

The detection and analysis of transient astronomical sources is of great importance to understand their time evolution. Traditional pipelines identify transient sources from difference (D) images derived by subtracting prior-observed…

Weakly supervised semantic segmentation (WSSS), a fundamental computer vision task, which aims to segment out the object within only class-level labels. The traditional methods adopt the CNN-based network and utilize the class activation…

Recently, the convolutional neural network has brought impressive improvements for object detection. However, detecting tiny objects in large-scale remote sensing images still remains challenging. First, the extreme large input size makes…

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…

Medical image segmentation (MIS) aims to finely segment various organs. It requires grasping global information from both parts and the entire image for better segmenting, and clinically there are often certain requirements for segmentation…

This paper delves into the challenges and advancements in the field of medical image segmentation, particularly focusing on breast cancer diagnosis. The authors propose a novel Transformer-based segmentation model that addresses the…

This paper proposes a neural rendering approach that represents a scene as "compressed light-field tokens (CLiFTs)", retaining rich appearance and geometric information of a scene. CLiFT enables compute-efficient rendering by compressed…

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

Convolutional Neural Networks (CNN) has achieved a great success in image recognition task by automatically learning a hierarchical feature representation from raw data. While the majority of Time-Series Classification (TSC) literature is…

Recent studies have integrated convolutions into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolution prevents it from dynamically adapting to input…

A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi-scale object detection. The MS-CNN consists of a proposal sub-network and a detection sub-network. In the proposal sub-network, detection is…

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened…

Semantic segmentation of remotely sensed urban scene images is required in a wide range of practical applications, such as land cover mapping, urban change detection, environmental protection, and economic assessment.Driven by rapid…

Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead, significantly restricts their practical deployments on…

Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Transformer-based deep neural networks have achieved remarkable success across various computer vision tasks, largely attributed to their long-range self-attention mechanism and scalability. However, most transformer architectures embed…