# Scaling Wide Residual Networks for Panoptic Segmentation

arXiv: https://arxiv.org/abs/2011.11675 · HTML: https://mlsanity.com/paper/2011.11675/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 30 of 32)

- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP](https://mlsanity.com/paper/2308.02487/) (2023)
- [A Generalist Framework for Panoptic Segmentation of Images and Videos](https://mlsanity.com/paper/2210.06366/) (2022)
- [CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation](https://mlsanity.com/paper/2206.08948/) (2022)
- [MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models](https://mlsanity.com/paper/2210.01820/) (2022)
- [Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation](https://mlsanity.com/paper/2104.05239/) (2021)
- [MP-Former: Mask-Piloted Transformer for Image Segmentation](https://mlsanity.com/paper/2303.07336/) (2023)
- [TubeFormer-DeepLab: Video Mask Transformer](https://mlsanity.com/paper/2205.15361/) (2022)
- [PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain](https://mlsanity.com/paper/2306.04557/) (2023)
- [ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion](https://mlsanity.com/paper/2308.07009/) (2023)
- [MGNet: Monocular Geometric Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2206.13199/) (2022)
- [DeepLab2: A TensorFlow Library for Deep Labeling](https://mlsanity.com/paper/2106.09748/) (2021)
- [Panoptic Segmentation: A Review](https://mlsanity.com/paper/2111.10250/) (2021)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)
- [PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation](https://mlsanity.com/paper/2206.00468/) (2022)
- [kMaX-DeepLab: k-means Mask Transformer](https://mlsanity.com/paper/2207.04044/) (2022)
- [Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning](https://mlsanity.com/paper/2306.01980/) (2023)
- [Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning](https://mlsanity.com/paper/2307.14786/) (2023)
- [MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation](https://mlsanity.com/paper/2312.06052/) (2023)
- [CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings](https://mlsanity.com/paper/2412.07377/) (2024)
- [The Missing Point in Vision Transformers for Universal Image Segmentation](https://mlsanity.com/paper/2505.19795/) (2025)
- [Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings](https://mlsanity.com/paper/2505.23395/) (2025)
- [PanDepth: Joint Panoptic Segmentation and Depth Completion](https://mlsanity.com/paper/2212.14180/) (2022)
- [RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation](https://mlsanity.com/paper/2305.01255/) (2023)
- [Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks](https://mlsanity.com/paper/2307.14179/) (2023)
- [Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation](https://mlsanity.com/paper/2412.10292/) (2024)
- [Stateless actor-critic for instance segmentation with high-level priors](https://mlsanity.com/paper/2107.02600/) (2021)
- [Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms](https://mlsanity.com/paper/2107.05637/) (2021)
- [Deep Residual Axial Networks](https://mlsanity.com/paper/2301.04631/) (2023)

## Abstract (arXiv)

The Wide Residual Networks (Wide-ResNets), a shallow but wide model variant of the Residual Networks (ResNets) by stacking a small number of residual blocks with large channel sizes, have demonstrated outstanding performance on multiple dense prediction tasks. However, since proposed, the Wide-ResNet architecture has barely evolved over the years. In this work, we revisit its architecture design for the recent challenging panoptic segmentation task, which aims to unify semantic segmentation and instance segmentation. A baseline model is obtained by incorporating the simple and effective Squeeze-and-Excitation and Switchable Atrous Convolution to the Wide-ResNets. Its network capacity is further scaled up or down by adjusting the width (i.e., channel size) and depth (i.e., number of layers), resulting in a family of SWideRNets (short for Scaling Wide Residual Networks). We demonstrate that such a simple scaling scheme, coupled with grid search, identifies several SWideRNets that significantly advance state-of-the-art performance on panoptic segmentation datasets in both the fast model regime and strong model regime.