Matthieu Cord

Professor at Sorbonne University, (ex UPMC, ex Paris 6, ex …)

Researcher in the MLIA team at ISIR lab.

Part-time principal scientist at

AI chair holder: VISA-DEEP Towards visual reasoning in deep learning (selected as a chair of research and teaching in artificial intelligence in the National French Government program on AI)

IUF honorary member (Promo Junior 2009), Scientific advisor at the French National Research Agency ANR for Artificial Intelligence (2017-2018), Project manager at CNRS (INS2I) (2015-2017)

My research interests include: Image Processing, Computer Vision, Machine Learning , Deep Learning, Pattern Recognition, Artificial Intelligence, Multimedia, Computational Cooking.


Crazy about cooking, ready to cook anywhere, anything, even my computer. Currently cooking on ANR VISIIR PROJECT for Web food recipe filtering, and searching.

Try the demo food reco engine!

Recent news


1 paper accepted to ICML on Model Ratatouille: Recycling Diverse Models for ood
4 papers accpted at CVPR on Counterfactual Explanations, Semantic and Panoptic Segmentation, Visual Recognition, Improving Selective VQA and 2 papers accepted at ICLR conf. on Image editing with diffusion models and Data free quantization of deep nets

AndrewYNg’s news letter pointed out our recent strategy for training Transformers in Vision: Cookbook for Vision Transformers: Good insight about our DeiT III !

1 IJCV paper on Explainability of vision-based autonomous driving systems: Review and challenges

Google Scholar profile

2022 main publi/infos:

Dec.: 2 papers presented at NeurIPS, 1 paper at CoRL
Nov.: 1 paper at BMVC Conference Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment!
Oct: 3 papers presented at ECCV including STEEX! and 2 papers about DeiT
July: 1 paper at ICML Fishr: Invariant Gradient Variances for Out-of-distribution Generalization
June: 2 papers at CVPR 1- Flexible Semantic Image Translation, 2- Transformers for continual learning + 8 workshop papers:
T-FOOD Transformer for Cross-Modal Food Retrieval,
Raising context awareness in motion forecasting,
Embedding Arithmetic of Multimodal Queries for Image Retrieval,
Towards efficient feature sharing in MIMO architectures,
Dynamic Query Selection for Fast Visual Perceiver,
Swapping Semantic Contents for Mixing Images,
Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation
and RED++: Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging published T-PAMI
Janv. 2022 MLIA is joigning the ISIR lab of Sorbonne University, it is a fantastic opportunuity with a lot of new challenges for us!

2021 main publications:

2 NeurIPS – Data-Free Compression of Deep Neural Networks and on Efficient Black-box Explanations for deep nets
5 ICCV – domain adaptation, bias, Mixing and data augmentation, self supervised, transformers (Xtarget Domain adaptation, Bias and Xmodal shortcuts, CaiT Deeper with transformers, Deep ensembles with 1 net, Coarse labels but fine-grained classification )
1 ICML – DeiT data-efficient image transformers
3 CVPR – Continual Semantic Segmentation, Semantic editing GANs, and Self Supervised BoW + workshops: Insights from the Future for Continual Learning at CVPR workshop on continual learning in computer vision, Learning Reasoning Mechanisms for Unbiased Question-based Counting at CVPR workshop on VQA
1 ICLR – diversity in deep ensembles
1 BMVC – GAN editing
1 PAMI – confidence for deep
and others …
1 IEEE Trans on Intelligent Transportation Systems – Detecting 32 Pedestrian Attributes for Autonomous Vehicles
1 CVIU zero-shot semantic segmentation with domain adaptation published in CVIU

1 paper BEEF on XAI and Autonomous driving at the NeurIPS workshop: Machine Learning for Autonomous Driving

My GANified Face (Thanks to Asya Grechka )


(+33) 1 44 27 71 39
Fax: (+33) 1 44 27 70 00
ISIR / Sorbonne University
4, place Jussieu
75005 Paris, France