# Understanding Convolution for Semantic Segmentation

arXiv: https://arxiv.org/abs/1702.08502 · HTML: https://mlsanity.com/paper/1702.08502/

## Key facts

- Cited by 168 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2017.

## Built on by (most cited first, 30 of 168)

- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://mlsanity.com/paper/2104.01431/) (2021)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [Are we ready for a new paradigm shift? A Survey on Visual Deep MLP](https://mlsanity.com/paper/2111.04060/) (2021)
- [EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation](https://mlsanity.com/paper/2106.15277/) (2021)
- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2304.10410/) (2023)
- [SKFlow: Learning Optical Flow with Super Kernels](https://mlsanity.com/paper/2205.14623/) (2022)
- [TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline](https://mlsanity.com/paper/2202.08471/) (2022)
- [AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling](https://mlsanity.com/paper/2111.00772/) (2021)
- [RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images](https://mlsanity.com/paper/2103.02184/) (2021)
- [Polarized Self-Attention: Towards High-quality Pixel-wise Regression](https://mlsanity.com/paper/2107.00782/) (2021)
- [DCAN: Improving Temporal Action Detection via Dual Context Aggregation](https://mlsanity.com/paper/2112.03612/) (2021)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.10026/) (2022)
- [You Only Learn Once: Universal Anatomical Landmark Detection](https://mlsanity.com/paper/2103.04657/) (2021)
- [CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data](https://mlsanity.com/paper/2112.09081/) (2021)
- [Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation](https://mlsanity.com/paper/2211.06866/) (2022)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN](https://mlsanity.com/paper/2309.01439/) (2023)
- [Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis](https://mlsanity.com/paper/2112.12349/) (2021)
- [Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration](https://mlsanity.com/paper/2106.07910/) (2021)
- [Fourier Document Restoration for Robust Document Dewarping and Recognition](https://mlsanity.com/paper/2203.09910/) (2022)
- [ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images](https://mlsanity.com/paper/2102.02531/) (2021)
- [Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network](https://mlsanity.com/paper/2104.06815/) (2021)
- [Modality specific U-Net variants for biomedical image segmentation: A survey](https://mlsanity.com/paper/2107.04537/) (2021)
- [CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters](https://mlsanity.com/paper/2203.15331/) (2022)

## Abstract (arXiv)

Recent advances in deep learning, especially deep convolutional neural networks (CNNs), have led to significant improvement over previous semantic segmentation systems. Here we show how to improve pixel-wise semantic segmentation by manipulating convolution-related operations that are of both theoretical and practical value. First, we design dense upsampling convolution (DUC) to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling. Second, we propose a hybrid dilated convolution (HDC) framework in the encoding phase. This framework 1) effectively enlarges the receptive fields (RF) of the network to aggregate global information; 2) alleviates what we call the "gridding issue" caused by the standard dilated convolution operation. We evaluate our approaches thoroughly on the Cityscapes dataset, and achieve a state-of-art result of 80.1% mIOU in the test set at the time of submission. We also have achieved state-of-the-art overall on the KITTI road estimation benchmark and the PASCAL VOC2012 segmentation task. Our source code can be found at https://github.com/TuSimple/TuSimple-DUC .