Hello!

Welcome to this portfolio

All projects

CASE STUDY 07

  • Academic
  • Computer Vision
  • Machine Learning

Bringing day and night closer

Domain adaptation with a bidirectional CycleGAN.

Personal / academic project

PyTorchOpenCVCycleGAN

The project, step by step

−74%accuracy gap between domains

  1. 01

    Day and night images

    Caltech Camera Traps

  2. 02

    Adapt the domains

    CycleGAN: day ↔ night transformations

  3. 03

    Evaluate the gap

    Compare accuracy across both domains

−74% is the reduction in the accuracy gap between domains, not the final accuracy.

01

Context

Computer Vision project using the Caltech Camera Traps dataset, focused on domain adaptation between daytime and night-time images.

02

Problem

Daytime and night-time images have different visual conditions. The project aims to reduce the performance gap between these domains.

03

Data

Images from the Caltech Camera Traps dataset. No before-and-after examples were provided for this presentation.

04

Approach

I developed a bidirectional CycleGAN for adaptation between day and night domains.

05

Method

The general principle of a CycleGAN is to learn transformations in both directions with a cycle-consistency constraint. The details of the configuration used remain to be documented.

06

Results

A 74% reduction in the accuracy gap. This figure describes the reduction in the gap between domains, not the model's final accuracy.

07

Technologies

PyTorch, OpenCV and CycleGAN.

08

Lessons and limitations

The quality of transformed images, failure cases and detailed evaluation protocol remain to be documented.