# Exploiting CNNs for Semantic Segmentation with Pascal VOC

arXiv: https://arxiv.org/abs/2304.13216 · HTML: https://mlsanity.com/paper/2304.13216/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 7 references that are in the map.
- First posted on arXiv 26 Apr 2023.

## Builds on (most cited first, 6 of 6)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks](https://mlsanity.com/paper/1807.10225/) (2018)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [LadderNet: Multi-path networks based on U-Net for medical image segmentation](https://mlsanity.com/paper/1810.07810/) (2018)
- [Polyp Detection and Segmentation using Mask R-CNN: Does a Deeper Feature Extractor CNN Always Perform Better?](https://mlsanity.com/paper/1907.09180/) (2019)

## Built on by (most cited first, 2 of 2)

- [Loss Landscape Topology Reveals Why Simple Baselines are Competitive at 3D Point Cloud Segmentation Under Class Imbalance](https://mlsanity.com/paper/2607.21089/) (2026)
- [How Sampling Strategy Affects Imbalance Mitigation in LiDAR Segmentation: A Study of Structured vs. Random Point-Based Architectures](https://mlsanity.com/paper/2608.16673/) (2026)

## Abstract (arXiv)

In this paper, we present a comprehensive study on semantic segmentation with the Pascal VOC dataset. Here, we have to label each pixel with a class which in turn segments the entire image based on the objects/entities present. To tackle this, we firstly use a Fully Convolution Network (FCN) baseline which gave 71.31% pixel accuracy and 0.0527 mean IoU. We analyze its performance and working and subsequently address the issues in the baseline with three improvements: a) cosine annealing learning rate scheduler(pixel accuracy: 72.86%, IoU: 0.0529), b) data augmentation(pixel accuracy: 69.88%, IoU: 0.0585) c) class imbalance weights(pixel accuracy: 68.98%, IoU: 0.0596). Apart from these changes in training pipeline, we also explore three different architectures: a) Our proposed model -- Advanced FCN (pixel accuracy: 67.20%, IoU: 0.0602) b) Transfer Learning with ResNet (Best performance) (pixel accuracy: 71.33%, IoU: 0.0926 ) c) U-Net(pixel accuracy: 72.15%, IoU: 0.0649). We observe that the improvements help in greatly improving the performance, as reflected both, in metrics and segmentation maps. Interestingly, we observe that among the improvements, dataset augmentation has the greatest contribution. Also, note that transfer learning model performs the best on the pascal dataset. We analyse the performance of these using loss, accuracy and IoU plots along with segmentation maps, which help us draw valuable insights about the working of the models.