# Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

arXiv: https://arxiv.org/abs/1611.10080 · HTML: https://mlsanity.com/paper/1611.10080/

## Key facts

- Cited by 184 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2016.

## Built on by (most cited first, 30 of 184)

- [Understanding The Robustness in Vision Transformers](https://mlsanity.com/paper/2204.12451/) (2022)
- [PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition](https://mlsanity.com/paper/2403.17695/) (2024)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.08896/) (2021)
- [Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2105.08965/) (2021)
- [NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes](https://mlsanity.com/paper/2111.13260/) (2021)
- [Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.02664/) (2022)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes](https://mlsanity.com/paper/2101.06085/) (2021)
- [Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design](https://mlsanity.com/paper/2305.13035/) (2023)
- [Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast](https://mlsanity.com/paper/2110.07110/) (2021)
- [Scalable Vision Transformers with Hierarchical Pooling](https://mlsanity.com/paper/2103.10619/) (2021)
- [A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation](https://mlsanity.com/paper/2104.07256/) (2021)
- [Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2107.11787/) (2021)
- [Complementary Patch for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.03852/) (2021)
- [Video Instance Segmentation with a Propose-Reduce Paradigm](https://mlsanity.com/paper/2103.13746/) (2021)
- [Cross Language Image Matching for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02668/) (2022)
- [Adaptive Early-Learning Correction for Segmentation from Noisy Annotations](https://mlsanity.com/paper/2110.03740/) (2021)
- [Weakly Supervised Semantic Segmentation using Out-of-Distribution Data](https://mlsanity.com/paper/2203.03860/) (2022)
- [L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2204.03206/) (2022)
- [Pseudo-mask Matters in Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/2108.12995/) (2021)
- [Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2106.04054/) (2021)
- [CTNet: Context-based Tandem Network for Semantic Segmentation](https://mlsanity.com/paper/2104.09805/) (2021)
- [Deep Learning for Micro-expression Recognition: A Survey](https://mlsanity.com/paper/2107.02823/) (2021)
- [Multi-Layer Pseudo-Supervision for Histopathology Tissue Semantic Segmentation using Patch-level Classification Labels](https://mlsanity.com/paper/2110.08048/) (2021)
- [Polarized Self-Attention: Towards High-quality Pixel-wise Regression](https://mlsanity.com/paper/2107.00782/) (2021)
- [Incremental Learning in Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2112.01882/) (2021)
- [Training Larger Networks for Deep Reinforcement Learning](https://mlsanity.com/paper/2102.07920/) (2021)
- [Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2206.14383/) (2022)
- [Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2209.07761/) (2022)

## Abstract (arXiv)

The trend towards increasingly deep neural networks has been driven by a general observation that increasing depth increases the performance of a network. Recently, however, evidence has been amassing that simply increasing depth may not be the best way to increase performance, particularly given other limitations. Investigations into deep residual networks have also suggested that they may not in fact be operating as a single deep network, but rather as an ensemble of many relatively shallow networks. We examine these issues, and in doing so arrive at a new interpretation of the unravelled view of deep residual networks which explains some of the behaviours that have been observed experimentally. As a result, we are able to derive a new, shallower, architecture of residual networks which significantly outperforms much deeper models such as ResNet-200 on the ImageNet classification dataset. We also show that this performance is transferable to other problem domains by developing a semantic segmentation approach which outperforms the state-of-the-art by a remarkable margin on datasets including PASCAL VOC, PASCAL Context, and Cityscapes. The architecture that we propose thus outperforms its comparators, including very deep ResNets, and yet is more efficient in memory use and sometimes also in training time. The code and models are available at https://github.com/itijyou/ademxapp