No article text was recorded for this version.
sparse spatial convolution
Version 1 of 152 papers65 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Selective Convolutional Network: An Efficient Object Detector with Ignoring Background
- Blog: ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
- Blog: Fine-Grained Dynamic Head for Object Detection
- Blog: ESOD: Efficient Small Object Detection on High-Resolution Images
- Blog: ESPACE: Accelerating Convolutional Neural Networks via Eliminating Spatial and Channel Redundancy
- Blog: Dynamic Dual Gating Neural Networks
- Blog: Targeted Kernel Networks: Faster Convolutions with Attentive Regularization
- Blog: Boosting up Scene Text Detectors with Guided CNN
- Blog: Beyond Trade-Off: Accelerate FCN-Based Face Detector With Higher Accuracy
- Blog: Supervised Transformer Network for Efficient Face Detection
- Blog: BiMatting: Efficient Video Matting via Binarization
- Blog: DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
- Blog: Efficient Rural Building Segmentation via a Multilevel Decoding Network
- Blog: Decoupled Convolutions for CNNs
- Blog: Direct Dense Pose Estimation
- Blog: Deploying machine learning to assist digital humanitarians: making image annotation in OpenStreetMap more efficient
- Blog: Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking
- Blog: An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions
- Blog: Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata
- Blog: Physics-aware Roughness Optimization for Diffractive Optical Neural Networks
- Blog: PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
- Blog: CrossRoI: Cross-camera Region of Interest Optimization for Efficient Real Time Video Analytics at Scale
- Blog: Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference
- Blog: Content-Aware Convolutional Neural Networks
- Blog: Uncertainty-Guided Spatial Pruning Architecture for Efficient Frame Interpolation
- Blog: Dynamic Frame Interpolation in Wavelet Domain
- Blog: An Empirical Analysis of Range for 3D Object Detection
- Blog: AdaCon: Adaptive Context-Aware Object Detection for Resource-Constrained Embedded Devices
- Blog: CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data
- Blog: Accelerating Transformer Pre-training with 2:4 Sparsity
- Blog: Dedicated Inference Engine and Binary-Weight Neural Networks for Lightweight Instance Segmentation
- Blog: MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions
- Blog: Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
- Blog: Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions
- Blog: Irrelevant Pixels are Everywhere: Find and Exclude Them for More Efficient Computer Vision
- Blog: The Image Local Autoregressive Transformer
- Blog: Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks
- Blog: Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
- Blog: Monocular Semantic Scene Completion via Masked Recurrent Networks
- Blog: QuadConv: Quadrature-based convolutions with applications to non-uniform PDE data compression
- Blog: Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving
- Blog: Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis
- Blog: Locally Masked Convolution for Autoregressive Models
- Blog: Spatially Adaptive Computation Time for Residual Networks
- Blog: Dynamic Neural Networks: A Survey
- Blog: Adaptive Window Pruning for Efficient Local Motion Deblurring
- Blog: An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions
- Blog: PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference
- Blog: Training Strategies for Vision Transformers for Object Detection
- Blog: Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
- Blog: SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization
- Blog: Single Image Depth Prediction With Wavelet Decomposition
History & citation
Current · Permanent link
- This direction split from Spatially Sparse Computation for Efficient Convolutional Networks (54% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sparse_spatial_convolution_07569123,
title = {sparse spatial convolution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sparse-spatial-convolution/rdr_07569123425347219c0290cf7d8979fd},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_sparse_spatial_convolution_07569123_v1,
title = {sparse spatial convolution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sparse-spatial-convolution/rdr_07569123425347219c0290cf7d8979fd/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}