home.social

#idlab — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #idlab, aggregated by home.social.

  1. Accurate object localization at reduced annotation/computational cost?
    #TriLite achieves this by pairing a pre-trained backbone, with our #TriHead component which separates ambiguous, foreground and background features.

    The main highlights of #TriLite include:
    • State-of-the-art performance
    • < 1M trainable parameters
    • single-stage training

    We will be glad to get in touch at #CVPR2026 to discuss further.

    We thank #DEFRA for supporting this research

    #WSOL #CV
    #sqIRL #IDLab #UAntwerp

  2. Accurate object localization at reduced annotation/computational cost?
    #TriLite achieves this by pairing a pre-trained backbone, with our #TriHead component which separates ambiguous, foreground and background features.

    The main highlights of #TriLite include:
    • State-of-the-art performance
    • < 1M trainable parameters
    • single-stage training

    We will be glad to get in touch at #CVPR2026 to discuss further.

    We thank #DEFRA for supporting this research

    #WSOL #CV
    #sqIRL #IDLab #UAntwerp

  3. Accurate object localization at reduced annotation/computational cost?
    #TriLite achieves this by pairing a pre-trained backbone, with our #TriHead component which separates ambiguous, foreground and background features.

    The main highlights of #TriLite include:
    • State-of-the-art performance
    • < 1M trainable parameters
    • single-stage training

    We will be glad to get in touch at #CVPR2026 to discuss further.

    We thank #DEFRA for supporting this research

    #WSOL #CV
    #sqIRL #IDLab #UAntwerp

  4. Accurate object localization at reduced annotation/computational cost?
    #TriLite achieves this by pairing a pre-trained backbone, with our #TriHead component which separates ambiguous, foreground and background features.

    The main highlights of #TriLite include:
    • State-of-the-art performance
    • < 1M trainable parameters
    • single-stage training

    We will be glad to get in touch at #CVPR2026 to discuss further.

    We thank #DEFRA for supporting this research

    #WSOL #CV
    #sqIRL #IDLab #UAntwerp

  5. The review process of scientific articles is not perfect, but a way to improve is by contributing to it in a diligent manner.

    Proud to have an #ICML'26 gold reviewer in our research group #sqIRL
    Congrats Benjamin!

    #AI #ML #Science #PeerReview #Award
    #UAntwerp #IDLab

  6. The review process of scientific articles is not perfect, but a way to improve is by contributing to it in a diligent manner.

    Proud to have an #ICML'26 gold reviewer in our research group #sqIRL
    Congrats Benjamin!

    #AI #ML #Science #PeerReview #Award
    #UAntwerp #IDLab

  7. The review process of scientific articles is not perfect, but a way to improve is by contributing to it in a diligent manner.

    Proud to have an #ICML'26 gold reviewer in our research group #sqIRL
    Congrats Benjamin!

    #AI #ML #Science #PeerReview #Award
    #UAntwerp #IDLab

  8. The review process of scientific articles is not perfect, but a way to improve is by contributing to it in a diligent manner.

    Proud to have an #ICML'26 gold reviewer in our research group #sqIRL
    Congrats Benjamin!

    #AI #ML #Science #PeerReview #Award
    #UAntwerp #IDLab

  9. The review process of scientific articles is not perfect, but a way to improve is by contributing to it in a diligent manner.

    Proud to have an #ICML'26 gold reviewer in our research group #sqIRL
    Congrats Benjamin!

    #AI #ML #Science #PeerReview #Award
    #UAntwerp #IDLab

  10. Feeling rewarded... Honored to be among the Top Reviewers at #NeurIPS this year.

    #AI #ML #UAntwerp #sqIRL #IDLab #imec

  11. I'm happy to announce that our paper 'Leveraging recommendations for generation' was accepted at @icwe2021! @W3C_WoT @rml_io @grhsnd @GertjanDM @ThomasDelva @HeyPieter @Ben__DM @natadimou @IDLabResearch @imec_int @ResearchUGent