Search Results for author: Alexandre Rame

Found 5 papers, 2 papers with code

Fishr: Invariant Gradient Variances for Out-of-distribution Generalization

2 code implementations7 Sep 2021 Alexandre Rame, Corentin Dancette, Matthieu Cord

In this paper, we introduce a new regularization -- named Fishr -- that enforces domain invariance in the space of the gradients of the loss: specifically, the domain-level variances of gradients are matched across training domains.

Domain Generalization Out-of-Distribution Generalization

CORE: Color Regression for Multiple Colors Fashion Garments

no code implementations6 Oct 2020 Alexandre Rame, Arthur Douillard, Charles Ollion

The second stage combines a colorname-attention (dependent of the detected color) with an object-attention (dependent of the clothing category) and finally weights a spatial pooling over the image pixels' RGB values.

OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation

no code implementations6 Dec 2018 Alexandre Rame, Emilien Garreau, Hedi Ben-Younes, Charles Ollion

Similarly to self-training methods, the predictions of these initial detectors mitigate the missing annotations on the complementary datasets.

Domain Adaptation Object Detection +1

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