Multi-Scale Feature Fusion

Follow this topic Ask about this topic

Momentum

16 papers in the last four weeks, up 129% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 119

All topics

Rethinking Implicit Spatial Representation in Visuomotor Policy Learning
Jun 13, 2026Xiangyu Chen, Yuxuan Hu, Chuhao Zhou +1Visual Representation Learning Visuomotor Policy Learning
MARS Lab, Nanyang Technological University
Context-Guided Semantic Alignment for Feature Fusion Networks
Jun 12, 2026Hyungseop Lee, Jiho Lee, Woochul KangMulti-Scale Feature Fusion Object Detection
Department of Embedded Systems Engineering, Incheon National University, Yeonsu-gu 22012, South Korea
Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model
Jun 10, 2026Sk Muhammad Asif, Orhun AydinRemote Sensing Image Understanding Remote Sensing Small Object Detection
Earth, Atmospheric and Geospatial Science Saint Louis University Saint Louis, Missouri, USA
Building Change Detection in Earthquake: A Multi-Scale Interaction Network and A Change Detection Dataset
Jun 9, 2026Yunlong Liu, Zekai ZhangDisaster Damage Assessment Building Damage Assessment
School of Control Science and Engineering, Shandong University, Ji’nan 250061, China
Loss-Guided Adaptive Scale Refinement for Molecular Force Prediction
Jun 8, 2026Limin YuMachine Learning Interatomic Potentials Multi-Scale Feature Fusion
School of Medical Imaging, Division of Medical Technology, Tianjin Key Laboratory of Functional Imaging, Tianjin Medical University, Tianjin 300203, China
FMRFusion: Frequency-Aware Multi-View Representation Learning for Heterogeneous Image Fusion
Jun 6, 2026Tao Zhoua, Yunlong Liu, Qinghui Chen +6Multi-Source Image Fusion Infrared-Visible Image Fusion
Control Science and Engineering, Shandong University, Jinan, 250061, China · Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, 250061, China · School of Computer Science and Engineering, Macau University of Science and Technology, Macau, 999078, China +1
Step-adaptive multimodal fusion network with multi-scale cloud feature learning for ultra-short-term solar irradiance forecasting
Jun 4, 2026Jingxin Zhang Xiaoqin WangTime Series Forecasting Multi-Scale Feature Fusion
School of Automation, Southeast University, Nanjing, 210096, China
Multi-Scale Feature Attention Network for Polymer Classification Using Terahertz Spectroscopy
Jun 4, 2026Roshni Mahtani, Ilán Carretero, Laura Monroy +3Multi-Scale Feature Fusion Materials Science
Instituto Universitario de Investigaci´on e Innovaci´on en Tecnolog´ıa Centarada en el Ser Humano, HumanTech, Universitat Polit`ecnica de Val`encia, Valencia, Spain · Department of Electronic Technology, Universidad Carlos III de Madrid, Legan´es, Spain · Artikode Intelligence S.L., Valencia, Spain
Cross-Modality Feature Fusion Based on Structured State Space Duality for Multimodal Image Registration Network
Jun 2, 2026Zhikang Li, Yan Wu, Xin Hu +2Multi-Scale Feature Fusion Cross-Modal Feature Matching
Remote Sensing Image Processing and Fusion Group, School of Electronic Engineering, Xidian University, Xi’an 710071, China · National Key Laboratory of Radar Signal Processing, Xidian University, Xi’an 710071, China
Contrastive Augmented Transformer with Domain-specific Enhancement for Robust Multi-scenario Metal Surface Defect Detection
Jun 1, 2026Yiyao Liu, Wenxiao He, Liyuan Ren +1Contrastive Learning Data Augmentation
Glasgow College, University of Electronic Science and Technology of China, Chengdu, 611731, China · Institute of Applied Physics and Computational Mathematics, Beijing, China · Department of Industrial Engineering, Tsinghua University, Beijing, China
AMN: An Adaptive Multi-Scale Fusion Network with Boundary and Uncertainty Modeling for Nuclei Segmentation
May 31, 2026Spoorthi M, Suja PalaniswamyHistopathology Image Segmentation Hybrid CNN-Transformer Architectures
Department of Computer Science & Engineering, Amrita School of Computing, Bengaluru, Amrita Vishwa Vidyapeetham, India
Robust Contrastive Graph Clustering with Adaptive Local-Global Integration
May 27, 2026Lei Zhang, Fubo Sun, Haipeng Yang +2Graph Representation Learning Multi-Scale Feature Fusion
School of Computer Science and Technology, Anhui University · College of Management and Economics, Tianjin University
Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation
May 25, 2026İsmail Emre Canıtez, Özgür ErkentMulti-Source Image Fusion Multi-Scale Feature Fusion
Hacettepe University
SFR-Net: Learning Scale-Frustum Representations for Ultra-Wide Area Remote Sensing Image Segmentation
May 25, 2026Chuyu Zhong, Keyan Chen, Qinzhe Yang +3Remote Sensing Image Segmentation Multi-Scale Feature Fusion
Department of Aerospace Intelligent Science and Technology, School of Astronautics, Beihang University, Beijing 100191, China · Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies, Ministry of Education, Beihang University, Beijing 100191, China · College of Computing and Data Science, Nanyang Technological University, Singapore +1
MambaDSF: Multi-Scale SSM with Dilated Feature Fusion for Sonar Small Target Detection
May 24, 2026Hui Lin, Jiayi Li, Jing Wang +1Underwater Imaging Small Object Detection
School of Information Science and Engineering, Ocean University of China, Qingdao 266100, China · School of Information and Communication Technology, Griffith University, Nathan, QLD 4111, Australia
WLNO: Wavelet-Laplace Neural Operator for Solving Partial Differential Equations
May 23, 2026Muhammad Abid, Arth Sojitra, Omer SanPDE Solving Multi-Scale Feature Fusion
Department of Mechanical and Aerospace Engineering, University of Tennessee, Knoxville Knoxville, TN 37996, USA.
Gaze into the Details: Locality-Sensitive Enhancement for OCTA Retinal Vessel Segmentation
May 20, 2026Tuopusen Huang, Ding Ma, Xiangqian WuMedical Imaging Retinal Vessel Segmentation
Faculty of Computing Harbin Institute of Technology Harbin, China
WoundFormer: Multi-Scale Spatial Feature Fusion for Multi-Class Wound Tissue Segmentation
May 19, 2026Muhammad Ashad Kabir, Rabin DulalMulti-Scale Feature Fusion Medical Image Segmentation
School of Computing, Mathematics and Engineering, Charles Sturt University, NSW, Australia
scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement
May 18, 2026Xichen Yan, Zelin Zang, Changxi Chi +8Representation Disentanglement Multi-Scale Feature Fusion
Jinan University · Westlake University · HKISI +1
EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution
May 17, 2026Hanli Zhao, Binhao Wang, Shihao Zhao +3Multi-Scale Feature Fusion Image Super-Resolution
College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325000, China · vivo BlueImage Lab, vivo Mobile Communication Co., Ltd, Shanghai 200100, China · College of Engineering and Computer Science, Australian National University, Canberra, Australia +1
Axial-Relation Guided Fusion State Space Model for Optical-Elevation Sensing Image Segmentation
May 16, 2026Feng Gao, Zhilin Jin, Yanhai Gan +2Image Segmentation Remote Sensing Image Segmentation
State Key Laboratory of Physical Oceanography, Ocean University of China, Qingdao 266100, China · Department of Electrical and Computer Engineering, Mississippi State University, Starkville, MS 39762 USA
Quantum Feature Pyramid Gating for Seismic Image Segmentation
May 14, 2026Taha Gharaibeh, Jyotsna SharmaImage Segmentation Hybrid Quantum-Classical ML
Louisiana State University Baton Rouge, Louisiana, USA
MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation
May 12, 2026Qing Cheng, Damiano Bertolini, Wei Zhang +3Image Segmentation Panoptic Segmentation
Technical University of Munich · Munich Center for Machine Learning (MCML) · Polytechnic University of Milan +3
M3Net: A Macro-to-Meso-to-Micro Clinical-inspired Hierarchical 3D Network for Pulmonary Nodule Classification
May 12, 2026Jinyue Li, Yuzhou Yu, Jingjing Yang +73D Medical Imaging Hierarchical Representation Learning
Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, 230031, PR China · University of Science and Technology of China, Hefei, 230026, PR China · Graduate School, Bengbu Medical College, Bengbu, 233030, PR China +4
Dual-Scale Temporal Fusion Reveals Structured Predictability in Subseasonal-to-Seasonal Temperature Prediction
May 7, 2026Elnaz Bashir, Jiali Wang, Lin YanTime Series Forecasting Multi-Scale Feature Fusion
Department of Computer Science, Iowa State University, Ames, IA 50011, USA · Environmental Science Division, Argonne National Laboratory, Lemont, IL 60439, USA
Deep Wave Network for Modeling Multi-Scale Physical Dynamics
May 5, 2026Alexander I. Khrabry, Edward A. Startsev, Andrew T. Powis +1U-Net Multi-Scale Feature Fusion
Princeton University, Princeton, New Jersey 08544, USA · FusionSoft LLC, Lawrenceville, New Jersey 08648, USA · Princeton Plasma Physics Laboratory, Princeton, New Jersey 08540, USA
Laplacian Frequency Interaction Network for Rural Thematic Road Extraction
May 4, 2026Baiyan Chen, Weixin ZhaiMulti-Scale Feature Fusion
College of Information and Electrical Engineering China Agricultural University Beijing, China
MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting
May 4, 2026Ahmed CherifLong-Term Time Series Forecasting Multilayer Perceptrons
Independent Researcher, Tunis, Tunisia
M\textsuperscript{4}Fuse: Lightweight State-Space MoE with a Cross-Scale Gating Bridge for Brain Tumor Segmentation
May 4, 2026Meihua Zhou, Xinyu Tong, Li YangImage Segmentation Multi-Scale Feature Fusion
University of Chinese Academy of Sciences · 2Wannan Medical University
RAFNet: Region-Aware Fusion Network for Pansharpening
May 4, 2026Jianing Zhang, Zijian Zhou, Kai SunDynamic Convolution Frequency-Domain Feature Learning
College of Artificial Intelligence, Xi’an Jiaotong University, Xi’an 710049, China · School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an 710049, China

Jun 13, 2026, cs.ROJ/K move · Enter open · S save

Rethinking Implicit Spatial Representation in Visuomotor Policy Learning

Xiangyu Chen, Yuxuan Hu, Chuhao Zhou, Jianfei Yang

MARS Lab, Nanyang Technological University

Visual Representation Learning Visuomotor Policy Learning Multi-Scale Feature Fusion Robotic Manipulation Robot Imitation Learning

Open paper AskPDF arXiv

Generative model-based imitation learning has become a widely adopted paradigm for robotic manipulation, where policy performance depends critically on the conditioned visual representations. Although spatial softmax-based representations have been adopted in prior visuomotor policies, their effectiveness and underlying mechanisms remain insufficiently understood. This work rethinks the use of spatial softmax pooling: do such implicit spatial representations provide effective and stable visual features for robotic manipulation? Through systematic studies of different pooling methods in visual encoders, we find that this pooling operation produces compact and stable spatial representations, which outperform feature-value representations, despite using substantially fewer dimensions. Complementary saliency analysis further suggests that these spatial representations guide the encoder to focus more consistently on task-relevant regions. However, this advantage is limited by a representation bottleneck in current visual encoders: repeated downsampling operations weaken fine-grained spatial information before the action-generation module can use it, especially under low-resolution observations. Motivated by these findings, we propose PRISM, a visual encoder that preserves multiscale implicit spatial information through top-down cross-attention fusion. Experiments across multiple tasks and policy backbones show consistent improvements. In particular, on the low-resolution, high-precision ToolHang task, PRISM shows clear gains, improving the average success rate from 5.0% to 13.4% while increasing parameters by only 15.4%. These results support the use of multiscale implicit spatial representations as an effective and efficient design principle for robotic manipulation.

Momentum

Related topics

Latest papers 119