Contact Us
All Case Studies
Computer Vision

VOC Segmentation App with Custom U-Net

Pixel-level multi-class segmentation across all 21 Pascal VOC classes.

2025
OVERVIEW

The Project

A semantic-segmentation system that classifies every pixel in an image using a custom U-Net (ConvTranspose2d upsampling) on the Pascal VOC 2012 dataset, supporting all 21 classes — wrapped in a visual app for real-time exploration of predictions.

Objectives

  • Build a U-Net-style segmentation model from scratch.
  • Support all 21 VOC classes with pixel-wise accuracy.
  • Normalize mask colours and log results live; ship a visual testing tool.
  • Tools & Technologies

    PyTorch LightningCustom U-Net (Conv2d / ConvTranspose2d)Weights & BiasesMatplotlib
    METHODOLOGY

    The Approach

    1

    Parse and convert RGB mask labels into integer masks; preprocess and normalize.

    2

    Build encoder–bottleneck–decoder U-Net; train with validation + metric logging.

    3

    Use ModelCheckpoint to save the top models by validation IoU.

    4

    Display batches and side-by-side image/mask/prediction grids in the app.

    OUTCOME

    Results & Learnings

  • Stable training and validation IoU with consistent foreground segmentation (people, dogs, bikes).
  • A 3-panel app comparing input, mask, and prediction per epoch.
  • Key Learnings

    • RGB-mask → class decoding and batch normalization stabilize training.
    • Balancing performance with real-time logging is a core tradeoff.
    CONTACT US

    Let's Discuss YourNext Project

    Ready to build something exceptional? Share your idea and we'll respond with a clear plan, honest timeline, and competitive quote within 24 hours.