# Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters

arXiv: https://arxiv.org/abs/2009.12021 · HTML: https://mlsanity.com/paper/2009.12021/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Contextual Transformer Networks for Visual Recognition](https://mlsanity.com/paper/2107.12292/) (2021)
- [Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection](https://mlsanity.com/paper/2308.02983/) (2023)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets](https://mlsanity.com/paper/2310.10563/) (2023)
- [FalconNet: Factorization for the Light-weight ConvNets](https://mlsanity.com/paper/2306.06365/) (2023)
- [Co-domain Symmetry for Complex-Valued Deep Learning](https://mlsanity.com/paper/2112.01525/) (2021)
- [Encoding Semantic Priors into the Weights of Implicit Neural Representation](https://mlsanity.com/paper/2406.04178/) (2024)
- [Normalize Filters! Classical Wisdom for Deep Vision](https://mlsanity.com/paper/2506.04401/) (2025)
- [Decomposing and Coupling Saliency Map for Lesion Segmentation in Ultrasound Images](https://mlsanity.com/paper/2308.00947/) (2023)

## Abstract (arXiv)

Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations. We propose Tied Block Convolution (TBC) that shares the same thinner filters over equal blocks of channels and produces multiple responses with a single filter. The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules. Our extensive experimentation on classification, detection, instance segmentation, and attention demonstrates TBC's significant across-the-board gain over standard convolution and group convolution. The proposed TiedSE attention module can even use 64 times fewer parameters than the SE module to achieve comparable performance. In particular, standard CNNs often fail to accurately aggregate information in the presence of occlusion and result in multiple redundant partial object proposals. By sharing filters across channels, TBC reduces correlation and can effectively handle highly overlapping instances. TBC increases the average precision for object detection on MS-COCO by 6% when the occlusion ratio is 80%. Our code will be released.