No article text was recorded for this version.
cross-scale weight sharing
Version 1 of 1133 papers171 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Recurrent Multi-scale Transformer for High-Resolution Salient Object Detection
- Blog: Locally Scale-Invariant Convolutional Neural Networks
- Blog: MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition
- Blog: XVFI: eXtreme Video Frame Interpolation
- Blog: Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression
- Blog: OctFusion: Octree-based Diffusion Models for 3D Shape Generation
- Blog: GuidedNet: A General CNN Fusion Framework via High-Resolution Guidance for Hyperspectral Image Super-Resolution
- Blog: Scale-aware Two-stage High Dynamic Range Imaging
- Blog: Learning by Analogy: Reliable Supervision From Transformations for Unsupervised Optical Flow Estimation
- Blog: A Unified Pyramid Recurrent Network for Video Frame Interpolation
- Blog: MultiResFormer: Transformer with Adaptive Multi-Resolution Modeling for General Time Series Forecasting
- Blog: Three-branch and Mutil-scale learning for Fine-grained Image Recognition (TBMSL-Net)
- Blog: Meta Segmentation Network for Ultra-Resolution Medical Images
- Blog: GCD-Sampling: A General Cross-scale Decoupled Sampling for Point Cloud
- Blog: Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
- Blog: Scale-Recurrent Network for Deep Image Deblurring
- Blog: Multigrid Predictive Filter Flow for Unsupervised Learning on Videos
- Blog: Gaussian Kernel Mixture Network for Single Image Defocus Deblurring
- Blog: Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid.
- Blog: Enhanced Deep Residual Networks for Single Image Super-Resolution
- Blog: V-DESIRR: Very Fast Deep Embedded Single Image Reflection Removal
- Blog: HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection
- Blog: DetectoRS: Detecting Objects With Recursive Feature Pyramid and Switchable Atrous Convolution
- Blog: Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections
- Blog: Dynamic Multi-Scale Semantic Segmentation based on Dilated Convolutional Networks
- Blog: Lightweight Yet Precized: A Redesigned YOLO for High-Accuracy Road Crack Detection on Vehicle-Mounted Devices
- Blog: Exploring Multi-Scale Feature Propagation and Communication for Image Super Resolution
- Blog: Multi-Scale Video Frame-Synthesis Network with Transitive Consistency Loss
- Blog: A Flexible Recurrent Residual Pyramid Network for Video Frame Interpolation
- Blog: Autofocus Layer for Semantic Segmentation
- Blog: Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
- Blog: LowDiff: Efficient Diffusion Sampling with Low-Resolution Condition
- Blog: SAFE: Scale Aware Feature Encoder for Scene Text Recognition
- Blog: Dynamic Fractal Mamba: A Neural Renormalization Group Flow for Scale-Invariant Sequence Modeling
- Blog: Saccadic Vision for Fine-Grained Visual Classification
- Blog: FocusCut: Diving into a Focus View in Interactive Segmentation
- Blog: FSS-YOLO: The Lightweight Drill Pipe Detection Method Based on YOLOv8n-obb
- Blog: Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
- Blog: SinDDM: A Single Image Denoising Diffusion Model
- Blog: ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm
- Blog: SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss
- Blog: Geometric Image Correspondence Verification by Dense Pixel Matching
- Blog: Enhanced Correlation Matching Based Video Frame Interpolation
- Blog: TINC: Tree-Structured Implicit Neural Compression
- Blog: Efficient Feature Extraction for High-resolution Video Frame Interpolation
- Blog: EfficientTDNN: Efficient Architecture Search for Speaker Recognition in the Wild
- Blog: In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images
- Blog: Scale-recurrent Network for Deep Image Deblurring
- Blog: K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
- Blog: Deep Video Super-Resolution using HR Optical Flow Estimation
- Blog: TRAR: Routing the Attention Spans in Transformer for Visual Question Answering
- Blog: RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
- Blog: SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks
- Blog: Investigating kernel shapes and skip connections for deep learning-based harmonic-percussive separation
- Blog: FILM: Frame Interpolation for Large Motion
- Blog: Multi-scale Generative Modeling for Fast Sampling
- Blog: Matryoshka Representation Learning
- Blog: SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model
- Blog: PhaseNet for Video Frame Interpolation
- Blog: Multi-scale Recursive and Perception-Distortion Controllable Image Super-Resolution
Showing 60 of 133 papers.
History & citation
Current · Permanent link
- This direction split from Cross Scale Parameter Sharing in Hierarchical Architectures (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_scale_weight_sharing_87f5e194,
title = {cross-scale weight sharing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-scale-weight-sharing/rdr_87f5e194ad964b58b977e3a753b30dc7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_scale_weight_sharing_87f5e194_v1,
title = {cross-scale weight sharing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-scale-weight-sharing/rdr_87f5e194ad964b58b977e3a753b30dc7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}