Search Results for author: Mai Lan Ha

Found 4 papers, 1 papers with code

Improving CLIP Robustness with Knowledge Distillation and Self-Training

no code implementations19 Sep 2023 Clement Laroudie, Andrei Bursuc, Mai Lan Ha, Gianni Franchi

This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning.

Knowledge Distillation

Robust Semantic Segmentation with Superpixel-Mix

1 code implementation2 Aug 2021 Gianni Franchi, Nacim Belkhir, Mai Lan Ha, Yufei Hu, Andrei Bursuc, Volker Blanz, Angela Yao

Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation.

Data Augmentation Segmentation +2

Learning a Discriminant Latent Space with Neural Discriminant Analysis

no code implementations13 Jul 2021 Mai Lan Ha, Gianni Franchi, Emanuel Aldea, Volker Blanz

NDA transforms deep features to become more discriminative and, therefore, improves the performances in various tasks.

Classification Out-of-Distribution Detection

Deep Ranking with Adaptive Margin Triplet Loss

no code implementations13 Jul 2021 Mai Lan Ha, Volker Blanz

We propose a simple modification from a fixed margin triplet loss to an adaptive margin triplet loss.

Face Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.