Zero-shot and open-world learning

Our research in open-world perception focuses on developing models capable of recognizing and adapting to novel objects and scenarios, ensuring safe and reliable performance in the ever-changing real world.

Selected publications

  1. CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation
    Monika Wysoczańska, Oriane Siméoni, Michaël Ramamonjisoa, Andrei Bursuc, Tomasz Trzciński, Patrick Pérez
    European Conference on Computer Vision, 2024
    pdf Code
  2. SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
    Ioannis Kakogeorgiou, Spyros Gidaris, Konstantinos Karantzalos, and Nikos Komodakis
    Computer Vision and Pattern Recognition, 2024
    pdf Code
  3. CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free
    Monika Wysoczańska, Michaël Ramamonjisoa, Tomasz Trzciński, Oriane Siméoni
    Winter Conference on Applications of Computer Vision (WACV), 2024
    pdf Code
  4. PØDA: Prompt-driven Zero-shot Domain Adaptation
    Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
    International Conference on Computer Vision (ICCV), 2023
    pdf Code
  5. Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds
    Bjoern Michele, Alexandre Boulch, Gilles Puy, Maxime Bucher, and Renaud Marlet
    International Conference on 3D Vision (3DV), 2021
    pdf Code Slides
  6. Zero-Shot Semantic Segmentation
    Maxime Bucher, Tuan-Hung Vu, Matthieu Cord, and Patrick Pérez
    Neural Information Processing Systems (NeurIPS), 2019
    pdf Code