Methods › General › Skip Connection Blocks › EESP

Extremely Efficient Spatial Pyramid of Depth-wise Dilated Separable Convolutions

EESP

3 papers tagged archive 2025-07-28

Introduced by Sachin Mehta et al. in ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

An EESP Unit, or Extremely Efficient Spatial Pyramid of Depth-wise Dilated Separable Convolutions, is an image model block designed for edge devices. It was proposed as part of the ESPNetv2 CNN architecture.

This building block is based on a reduce-split-transform-merge strategy. The EESP unit first projects the high-dimensional input feature maps into low-dimensional space using groupwise pointwise convolutions and then learns the representations in parallel using depthwise dilated separable convolutions with different dilation rates. Different dilation rates in each branch allow the EESP unit to learn the representations from a large effective receptive field. To remove the gridding artifacts caused by dilated convolutions, the EESP fuses the feature maps using hierarchical feature fusion (HFF).

Paper Source See Code · osmr/imgclsmob

Papers archive 2025-07-28

3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Towards Efficient Resume Understanding: A Multi-Granularity Multi-Modal Pre-Training Approach
13 Apr 2024 · 0 repositories · arXiv:2404.13067
ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding
23 Mar 2023 · 1 repository · arXiv:2303.13186
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
28 Nov 2018 · 10 repositories · arXiv:1811.11431

Syntology ran 2 of 4 samples · 2 unverified

Tasks archive 2025-07-28

14 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
3D visual grounding	1
General Classification	1
Image Classification	1
Language Modeling	1
Language Modelling	1
Object	1
Object Detection	1
Real-Time Object Detection	1
Real-Time Semantic Segmentation	1
Semantic Segmentation	1
Visual Grounding	1
document understanding	1
image-classification	1
object-detection	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (3 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Skip Connection Blocks Image Model Blocks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections