Related papers: LoFLAT: Local Feature Matching using Focused Linea…
Adapting vision transformer foundation models through parameter-efficient fine-tuning (PEFT) methods has become increasingly popular. These methods optimize a limited subset of parameters, enabling efficient adaptation without the need to…
Federated Learning (FL) aims to learn a single global model that enables the central server to help the model training in local clients without accessing their local data. The key challenge of FL is the heterogeneity of local data in…
Learning semantic correspondence between image and text is significant as it bridges the semantic gap between vision and language. The key challenge is to accurately find and correlate shared semantics in image and text. Most existing…
We address the problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression. Many recent works utilize Transformer to extract features for the target object by aggregating…
Correlation acts as a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion manner to consider the similarity between the template and the search region.…
Current medical image segmentation approaches have limitations in deeply exploring multi-scale information and effectively combining local detail textures with global contextual semantic information. This results in over-segmentation,…
Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a reasonable and broader receptive field is essential for…
Feature matching is a cornerstone task in computer vision, essential for applications such as image retrieval, stereo matching, 3D reconstruction, and SLAM. This survey comprehensively reviews modality-based feature matching, exploring…
Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are based on Convolutional Neural Networks (CNNs). Despite…
In the field of multi-organ medical image segmentation, recent methods frequently employ Transformers to capture long-range dependencies from image features. However, these methods overlook the high computational cost of Transformers and…
Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…
Deformable image registration is a critical technology in medical image analysis, with broad applications in clinical practice such as disease diagnosis, multi-modal fusion, and surgical navigation. Traditional methods often rely on…
Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches…
The research on recognizing the most discriminative regions provides referential information for weakly supervised object localization with only image-level annotations. However, the most discriminative regions usually conceal the other…
Although face recognition (FR) has achieved great success in recent years, it is still challenging to accurately recognize faces in low-quality images due to the obscured facial details. Nevertheless, it is often feasible to make…
We revisit the problem of training attention-based sparse image matching models for various local features. We first identify one critical design choice that has been previously overlooked, which significantly impacts the performance of the…
Multi-modal systems enhance performance in autonomous driving but face inefficiencies due to indiscriminate processing within each modality. Additionally, the independent feature learning of each modality lacks interaction, which results in…
While attention-based approaches have shown considerable progress in enhancing image fusion and addressing the challenges posed by long-range feature dependencies, their efficacy in capturing local features is compromised by the lack of…
Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…
Multi-modal learning has been intensified in recent years, especially for applications in facial analysis and action unit detection whilst there still exist two main challenges in terms of 1) relevant feature learning for representation and…