June: our paper RED++: Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging published T-PAMI
May: 1 paper accepted to ICML 2022: Fishr: Invariant Gradient Variances for Out-of-distribution Generalization
April: 8 papers accepted to CVPR workshops! including
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
March: 2 papers accepted to CVPR 2022: 1- Flexible Semantic Image Translation, 2- Transformers for continual learning
Janv. 2022 MLIA is joigning the ISIR lab of Sorbonne University, it is a fantastic opportunuity with a lot of new challenges for us!
Dec.: NeurIPS 2021 with 2 papers presented on Data-Free Compression of Deep Neural Networks and on Efficient Black-box Explanations for deep nets!
1 paper presented at BMVC conf. on GAN editing
Our paper Detecting 32 Pedestrian Attributes for Autonomous Vehicles accepted for publication in IEEE Transactions on Intelligent Transportation Systems
Our paper zero-shot semantic segmentation with domain adaptation published in CVIU
Five papers accepted at ICCV 2021, Xtarget Domain adaptation, Bias and Xmodal shortcuts, CaiT Deeper with transformers, Deep ensembles with 1 net, Coarse labels but fine-grained classification – congrats to my students !!!!!
Our paper on transformers for Vision DeiT accepted to ICML 2021!
Our paper Insights from the Future for Continual Learning accepted at the CVPR workshop on continual learning in computer vision
Our paper Learning Reasoning Mechanisms for Unbiased Question-based Counting will be presented at the CVPR workshop on VQA
1 arXiv paper on Explainability of vision-based autonomous driving systems: Review and challenges
1 paper BEEF on XAI and Autonomous driving at the NeurIPS workshop: Machine Learning for Autonomous Driving
Google Scholar profile
2021 main publications:
5 ICCV – domain adaptation, bias, Mixing and data augmentation, self supervised, transformers
1 ICML – data-efficient image transformers
3 CVPR – Continual Semantic Segmentation, Semantic editing GANs, and Self Supervised BoW
1 ICLR – diversity in deep ensembles
1 PAMI journal – confidence for deep
and others …
My GANified Face (Thanks to Asya Grechka )