Publications

You can find my complete articles list on my Google Scholar profile.

[ECCV 2024] : Su S.; Lin X.; Doan, T.; Behpour S.; He W.; Gou L.; Miao F.; Ren L.; MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks

[CVPR 2024] : Wang X.; He W.; Xuan X.; Sebastian C.; Ono J.; Li X.; Behpour S.; Doan, T.; Gou L.; Wei Shen H.; Ren L.; USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation
[Video]

[AAAI 2024] : Doan, T.; Li, X.; Behpour, S., Wenbin, H.; Gou L.; Ren L.; Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection.
[Code] [Poster] [Video]

[NeurIPS 2023] : Behpour, S.; Doan, T.; Li, X.; Wenbin, H.; Gou L.; Ren L.; GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients.
[Poster] [Video]

[NeurIPS 2023] : Li, X.; Behpour, S.; Doan, T.; Wenbin, H.; Gou L.; Ren L.; UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models.
[Poster] [Video]

[ICLR 2023] : Gaya, J.; Doan, T.; Caccia, L., Soulier L.; Denoyer L. ; Raileanu, R.; Building a Subspace of Policies for Scalable Continual Learning.
[Code] [Video]

[CoLLAs 2023]: Doan, T.; Mirzadeh, I. ; Farajtabar, M.; Continual Learning Beyond a Single Model.

[JAIR 2022] : Doan, T.*; Mazoure, B.*; Pineau, J.; Precup, D.; Rabusseau, G.; Low-Rank Representation of Reinforcement Learning Policies.

[AISTATS 2021] : Doan, T.; Bennani, M.; Mazoure, B.; Rabusseau, G.; Alquier, P., A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix.

[ICLR 2021] : Jeon, W; Chen-Yan, S.; Barde, P.; Doan, T.; Nowrouzezahrai, D.; Pineau, J.; Regularized Inverse Reinforcement Learning.

[CBM 2021] : Abdar, M.; Samami, M.; Mahmoodabad, S; Doan, T; Mazoure, B; Hashemifesharaki, R.; Liu L.; Khosravi, A; Acharya; U.; Makarenkov, V.; Nahavandi, S; Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning.

[NeurIPS 2020] : Mazoure B.; Tachet des Combes R.; Doan, T.; Bachman P.; Hjelm, R D.; Deep Reinforcement and InfoMax Learning.

[CoRL 2019] : Doan, T.*; Mazoure, B.*; Durand, A.; Hjelm, R D.; Pineau, J.; Leveraging exploration in off-policy algorithms via normalizing flows.

[ICML 2019] : Monteiro, J.; Albuquerque, I., Doan, T.; Considine B., Falk T., Mitliagkas I.; Multi-objective training of Generative Adversarial Networks with multiple discriminators.

[AAAI 2019] : Doan, T.; Monteiro, J.; Albuquerque, I.; Mazoure, B.; Durand, A.; Hjelm, R D.; Pineau, J.; On-line Adaptative Curriculum Learning for GANs.