Related papers: FMNet: Frequency-Assisted Mamba-Like Linear Attent…
Object detection is widely studied in computer vision filed. In recent years, certain representative deep learning based detection methods along with solid benchmarks are proposed, which boosts the development of related researchs. However,…
Transformers have recently emerged as a significant force in the field of image deraining. Existing image deraining methods utilize extensive research on self-attention. Though showcasing impressive results, they tend to neglect critical…
Current image tampering localization methods primarily rely on Convolutional Neural Networks (CNNs) and Transformers. While CNNs suffer from limited local receptive fields, Transformers offer global context modeling at the expense of…
Cross-modal misalignments, such as spatial offsets, resolution discrepancies, and semantic deficiencies, frequently occur in visible-infrared object detection (VI-OD). To mitigate this, existing methods are typically adapted into an…
Few-shot object detection (FSOD) aims at learning a detector that can fast adapt to previously unseen objects with scarce annotated examples, which is challenging and demanding. Existing methods solve this problem by performing subtasks of…
Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify…
The process of fusing a high spatial resolution (HR) panchromatic (PAN) image and a low spatial resolution (LR) multispectral (MS) image to obtain an HRMS image is known as pansharpening. With the development of convolutional neural…
Image fusion aims to integrate complementary information across modalities to generate high-quality fused images, thereby enhancing the performance of high-level vision tasks. While global spatial modeling mechanisms show promising results,…
AI-generated images are becoming increasingly realistic and diverse, posing significant challenges for generalizable detection. While Vision Foundation Models (VFMs) provide rich semantic representations and frequency-based methods capture…
This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images despite limited training data. Existing frequency-based paradigms have relied on frequency-level…
Forensic analysis of manipulated pixels requires the identification of various hidden and subtle features from images. Conventional image recognition models generally fail at this task because they are biased and more attentive toward the…
This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by…
As remote sensing imaging technology continues to advance and evolve, processing high-resolution and diversified satellite imagery to improve segmentation accuracy and enhance interpretation efficiency emerg as a pivotal area of…
Camouflaged Object Detection (COD) stands as a significant challenge in computer vision, dedicated to identifying and segmenting objects visually highly integrated with their backgrounds. Current mainstream methods have made progress in…
Previous video object segmentation approaches mainly focus on using simplex solutions between appearance and motion, limiting feature collaboration efficiency among and across these two cues. In this work, we study a novel and efficient…
Camouflaged Object Detection (COD) presents inherent challenges due to the subtle visual differences between targets and their backgrounds. While existing methods have made notable progress, there remains significant potential for…
Fully Convolutional Neural Network (FCN) has been widely applied to salient object detection recently by virtue of high-level semantic feature extraction, but existing FCN based methods still suffer from continuous striding and pooling…
Low-light image enhancement remains a persistent challenge in computer vision, where state-of-the-art models are often hampered by hardware constraints and computational inefficiency, particularly at high resolutions. While foundational…
The dynamic range limitation of conventional RGB cameras reduces global contrast and causes loss of high-frequency details such as textures and edges in complex traffic environments (e.g., nighttime driving, tunnels), hindering…
We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems. The architecture utilizes two networks: a low resolution…