Multi-scale Features Research Articles

Cross-scene classification of hyperspectral images poses significant challenges due to the lack of a priori knowledge and the differences in data distribution across scenes. While traditional studies have had limited use of a priori knowledge from other modalities, recent advancements in pre-trained large-scale language-vision models have shown strong performance on various downstream tasks, highlighting the potential of cross-modal assisted learning. In this paper, we propose a Semantic-aware Collaborative Parallel Network (SCPNet) to mitigate the impact of data distribution differences by incorporating linguistic modalities to assist in learning cross-domain invariant representations of hyperspectral images. SCPNet uses a parallel architecture consisting of a spatial–spectral feature extraction module and a multiscale feature extraction module, designed to capture rich image information during the feature extraction phase. The extracted features are then mapped into an optimized semantic space, where improved supervised contrastive learning clusters image features from the same category together while separating those from different categories. Semantic space bridges the gap between visual and linguistic modalities, enabling the model to mine cross-domain invariant representations from the linguistic modality. Experimental results demonstrate that SCPNet significantly outperforms existing methods on three publicly available datasets, confirming its effectiveness for cross-scene hyperspectral image classification tasks.

MambaRSIS: Context-aware multi-scale feature aggregation with selective state space model for remote sensing instance segmentation

Low-Light Image Enhancement Method based on Multiscale Feature Fusion

An attention-guided multi-scale feature cascade network for underwater fish counting

Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of images, leading to significant computational cost. To address this challenge, we propose a novel network architecture, called Parameter-Inverted Image Pyramid Networks (PIIP). Specifically, PIIP uses pretrained models (ViTs or CNNs) as branches to process multi-scale images, where images of higher resolutions are processed by smaller network branches to balance computational cost and performance. To integrate information from different spatial scales, we further propose a novel cross-branch feature interaction mechanism. To validate PIIP, we apply it to various perception models and a representative multimodal large language model called LLaVA, and conduct extensive experiments on various tasks such as object detection, segmentation, image classification and multimodal understanding. PIIP achieves superior performance compared to single-branch and existing multi-resolution approaches with lower computational cost. When applied to InternViT-6B, a large-scale vision foundation model, PIIP can improve its performance by 1%-2% on detection and segmentation with only 40%-60% of the original computation, finally achieving 60.0 box AP on MS COCO and 59.7 mIoU on ADE20 K. For multimodal understanding, our PIIP-LLaVA achieves 73.0% accuracy on TextVQA and 74.5% on MMBench with only 2.8 M training data.

A YOLOv11-based crack detection method for stamped parts with the use of multiscale feature fusion and adaptive downsampling

VMamba-Crowd: Bridging multi-scale features from Visual Mamba for weakly-supervised crowd counting

Multiscale feature decoupling via VMD and dual-channel networks for dissolved gas prediction in transformers

A deep learning framework for global transportation energy carbon emission forecasting: integrating generative pre-trained transformer with multi-scale feature analysis

Accurate pose estimation of non-cooperative space objects is crucial for applications such as satellite maintenance, space debris removal, and on-orbit assembly. However, monocular pose estimation methods face significant challenges in environments with limited visibility. Different from the traditional pose estimation methods that use images from a single band as input, we propose a novel deep learning-based pose estimation framework for non-cooperative space objects by fusing visible and infrared images. First, we introduce an image fusion subnetwork that integrates multi-scale features from visible and infrared images into a unified embedding space, preserving the detailed features of visible images and the intensity information of infrared images. Subsequently, we design a robust pose estimation subnetwork that leverages the rich information from the fused images to achieve accurate pose estimation. By combining these two subnetworks, we construct the Visible and Infrared Fused Pose Estimation Framework (VIPE) for non-cooperative space objects. Additionally, we present a Bimodal-Vision Pose Estimation (BVPE) dataset, comprising 3,630 visible-infrared image pairs, to facilitate research in this domain. Extensive experiments on the BVPE dataset demonstrate that VIPE significantly outperforms existing monocular pose estimation methods, particularly in complex space environments, providing more reliable and accurate pose estimation results.

3D-M2C-ResNet: A Multi-Scale feature enhancement and fusion model for Fine-Scale tree species classification in urban forests

LMFENet: A Hybrid Local-Global and Multi-Scale Feature Extraction Network for Oil Spill Type Classification Using Sentinel-1 Imagery

Multi-scale Feature Refinement via Perspective Scaling and Adaptive Regularization for text-based person search

Cascaded embedded-FPN: A cross-modality multi-scale feature fusion network for varied-sized objects semantic segmentation

SMAFusion: Multimodal medical image fusion based on spatial registration and local-global multi-scale feature adaptive fusion

Fast geometric deep learning for intraoperative soft tissue deformation estimation: Towards real-time AR guidance in liver surgery.

Dark-field intelligent detection of V. parahaemolyticus using T4 bacteriophage displaying tail spike proteins and gold nanoparticles.

S-YOLO: An enhanced small object detection method based on adaptive gating strategy and dynamic multi-scale focus module.

A cross-domain multi-scale feature fusion network based on graph convolution for intelligent fault diagnosis

A self-supervised model based on sequence information and multi-scale features advances agricultural soil CT image segmentation