Related papers: DyCAF-Net: Dynamic Class-Aware Fusion Network

Human attention mechanisms often work in a top-down manner, yet it is not well explored in vision research. Here, we propose the Top-Down Attention Framework (TDAF) to capture top-down attentions, which can be easily adopted in most…

Multi-modal medical image fusion is essential for the precise clinical diagnosis and surgical navigation since it can merge the complementary information in multi-modalities into a single image. The quality of the fused image depends on the…

Deep anomaly detection (AD) aims to provide robust and efficient classifiers for one-class and unbalanced settings. However current AD models still struggle on edge-case normal samples and are often unable to keep high performance over…

Change detection (CD) has extensive applications and is a crucial method for identifying and localizing target changes. In recent years, various CD methods represented by convolutional neural network (CNN) and transformer have achieved…

Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend…

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite…

Out-of-distribution (OOD) detection remains a fundamental challenge for deep neural networks, particularly due to overconfident predictions on unseen OOD samples during testing. We reveal a key insight: OOD samples predicted as the same…

Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient…

Deepfakes have emerged as a significant threat to digital media authenticity, increasing the need for advanced detection techniques that can identify subtle and time-dependent manipulations. CNNs are effective at capturing spatial artifacts…

Accurate remote sensing-based crop yield prediction remains a fundamental challenging task due to complex spatial patterns, heterogeneous spectral characteristics, and dynamic agricultural conditions. Existing methods often suffer from…

For many computer vision applications, such as image description and human identification, recognizing the visual attributes of humans is an essential yet challenging problem. Its challenges originate from its multi-label nature, the large…

3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on…

Expert systems often operate in domains characterized by class-imbalanced tabular data, where detecting rare but critical instances is essential for safety and reliability. While conventional approaches, such as cost-sensitive learning,…

Multi-modal emotion recognition is challenging due to the difficulty of extracting features that capture subtle emotional differences. Understanding multi-modal interactions and connections is key to building effective bimodal speech…

Past few years have witnessed exponential growth of interest in deep learning methodologies with rapidly improving accuracies and reduced computational complexity. In particular, architectures using Convolutional Neural Networks (CNNs) have…

Language Models pretrained on large textual data have been shown to encode different types of knowledge simultaneously. Traditionally, only the features from the last layer are used when adapting to new tasks or data. We put forward that,…

Computer-aided diagnosis has recently received attention for its advantage of low cost and time efficiency. Although deep learning played a major role in the recent success of acne detection, there are still several challenges such as color…

Unmanned aerial vehicle (UAV) object detection plays a vital role in applications such as environmental monitoring and urban security. To improve robustness, recent studies have explored multimodal detection by fusing visible (RGB) and…

Real-world fine manipulation, particularly in bimanual manipulation, typically requires low-latency control and stable visual localization, while collecting large-scale data is costly and limited demonstrations may lead to localization…

Semantic segmentation of histopathology images under class imbalance is typically addressed through frequency-based loss reweighting, which implicitly assumes that rare classes are difficult. However, true difficulty also arises from…