# Superpixel Convolutional Networks using Bilateral Inceptions

arXiv: https://arxiv.org/abs/1511.06739 · HTML: https://mlsanity.com/paper/1511.06739/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2015.

## Built on by (most cited first, 23 of 23)

- [FeatUp: A Model-Agnostic Framework for Features at Any Resolution](https://mlsanity.com/paper/2403.10516/) (2024)
- [Decoupled Dynamic Filter Networks](https://mlsanity.com/paper/2104.14107/) (2021)
- [HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2305.13031/) (2023)
- [Learning Hierarchical Image Segmentation For Recognition and By Recognition](https://mlsanity.com/paper/2210.00314/) (2022)
- [Semantic Segmentation by Early Region Proxy](https://mlsanity.com/paper/2203.14043/) (2022)
- [Segmenting Transparent Object in the Wild with Transformer](https://mlsanity.com/paper/2101.08461/) (2021)
- [Superpixel Transformers for Efficient Semantic Segmentation](https://mlsanity.com/paper/2309.16889/) (2023)
- [HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation](https://mlsanity.com/paper/2106.03755/) (2021)
- [E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation](https://mlsanity.com/paper/2112.07106/) (2021)
- [Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation](https://mlsanity.com/paper/2201.01427/) (2022)
- [Trainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT](https://mlsanity.com/paper/2207.07368/) (2022)
- [Learning Invariant Inter-pixel Correlations for Superpixel Generation](https://mlsanity.com/paper/2402.18201/) (2024)
- [Lagrangian Motion Fields for Long-term Motion Generation](https://mlsanity.com/paper/2409.01522/) (2024)
- [Superpixel-based Refinement for Object Proposal Generation](https://mlsanity.com/paper/2101.04574/) (2021)
- [Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks](https://mlsanity.com/paper/2103.03435/) (2021)
- [SIN:Superpixel Interpolation Network](https://mlsanity.com/paper/2110.08702/) (2021)
- [Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA) for Remote Land-use Change Detection](https://mlsanity.com/paper/2303.14322/) (2023)
- [Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms](https://mlsanity.com/paper/2309.13438/) (2023)
- [MSP : Refine Boundary Segmentation via Multiscale Superpixel](https://mlsanity.com/paper/2112.01746/) (2021)
- [Content-aware Directed Propagation Network with Pixel Adaptive Kernel Attention](https://mlsanity.com/paper/2107.13144/) (2021)
- [Unsupervised Superpixel Generation using Edge-Sparse Embedding](https://mlsanity.com/paper/2211.15474/) (2022)
- [Superpixel Integrated Grids for Fast Image Segmentation](https://mlsanity.com/paper/2510.06487/) (2025)
- [Semantic segmentation with coarse annotations](https://mlsanity.com/paper/2510.15756/) (2025)

## Abstract (arXiv)

In this paper we propose a CNN architecture for semantic image segmentation. We introduce a new 'bilateral inception' module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image. The feature spaces for bilateral filtering and other parameters of the module are learned end-to-end using standard backpropagation techniques. The bilateral inception module addresses two issues that arise with general CNN segmentation architectures. First, this module propagates information between (super) pixels while respecting image edges, thus using the structured information of the problem for improved results. Second, the layer recovers a full resolution segmentation result from the lower resolution solution of a CNN. In the experiments, we modify several existing CNN architectures by inserting our inception module between the last CNN (1x1 convolution) layers. Empirical results on three different datasets show reliable improvements not only in comparison to the baseline networks, but also in comparison to several dense-pixel prediction techniques such as CRFs, while being competitive in time.