Fei Zhu

Orcid: 0000-0003-3016-5538

Affiliations:
  • Chinese Academy of Sciences, Institute of Automation, Beijing, China
  • University of Chinese Academy of Sciences, School of Artificial Intelligence, Beijing, China


According to our database1, Fei Zhu authored at least 51 papers between 2021 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning.
IEEE Trans. Pattern Anal. Mach. Intell., August, 2025

MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark.
CoRR, August, 2025

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery.
IEEE Trans. Pattern Anal. Mach. Intell., July, 2025

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training.
CoRR, July, 2025

Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection.
IEEE Trans. Neural Networks Learn. Syst., June, 2025

A Comprehensive Survey on Continual Learning in Generative Models.
CoRR, June, 2025

LLaVA-c: Continual Improved Visual Instruction Tuning.
CoRR, June, 2025

MLLM-CL: Continual Learning for Multimodal Large Language Models.
CoRR, June, 2025

Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning.
CoRR, April, 2025

TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data.
CoRR, April, 2025

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery.
CoRR, April, 2025

Breaking the Limits of Reliable Prediction via Generated Data.
Int. J. Comput. Vis., March, 2025

Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Models.
CoRR, March, 2025

Global Convergence of Continual Learning on Non-IID Data.
CoRR, March, 2025

HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model.
CoRR, March, 2025

Federated Continual Instruction Tuning.
CoRR, March, 2025

Practical Continual Forgetting for Pre-trained Vision Models.
CoRR, January, 2025

Fourier Boundary Features Network With Wider Catchers for Glass Segmentation.
IEEE Trans. Image Process., 2025

Towards trustworthy dataset distillation.
Pattern Recognit., 2025

Class incremental learning with self-supervised pre-training and prototype learning.
Pattern Recognit., 2025

Practical incremental learning: Striving for better performance-efficiency trade-off.
Neurocomputing, 2025

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
Revisiting Confidence Estimation: Towards Reliable Failure Prediction.
IEEE Trans. Pattern Anal. Mach. Intell., May, 2024

DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning.
CoRR, 2024

ModalPrompt:Dual-Modality Guided Prompt for Continual Learning of Large Multimodal Models.
CoRR, 2024

Enhancing Outlier Knowledge for Few-Shot Out-of-Distribution Detection with Extensible Local Prompts.
CoRR, 2024

Multi-scale Unified Network for Image Classification.
CoRR, 2024

Towards Non-Exemplar Semi-Supervised Class-Incremental Learning.
CoRR, 2024

Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning.
CoRR, 2024

Continual Forgetting for Pre-trained Vision Models.
CoRR, 2024

Open-world Machine Learning: A Review and New Outlooks.
CoRR, 2024

Federated Class-Incremental Learning with Prototype Guided Transformer.
CoRR, 2024

Happy: A Debiased Learning Framework for Continual Generalized Category Discovery.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Delving into Feature Space: Improving Adversarial Robustness by Feature Spectral Regularization.
Proceedings of the Pattern Recognition - 27th International Conference, 2024

PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning.
Proceedings of the Computer Vision - ECCV 2024, 2024

RCL: Reliable Continual Learning for Unified Failure Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Active Generalized Category Discovery.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Dynamics-aware loss for learning with label noise.
Pattern Recognit., December, 2023

Imitating the oracle: Towards calibrated model for class incremental learning.
Neural Networks, July, 2023

Learning by Seeing More Classes.
IEEE Trans. Pattern Anal. Mach. Intell., June, 2023

Adversarial training with distribution normalization and margin balance.
Pattern Recognit., April, 2023

Training with scaled logits to alleviate class-level over-fitting in few-shot learning.
Neurocomputing, 2023

Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning.
CoRR, 2023

OpenMix: Exploring Outlier Samples for Misclassification Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Rethinking Confidence Calibration for Failure Prediction.
Proceedings of the Computer Vision - ECCV 2022, 2022

2021
Class-Incremental Learning via Dual Augmentation.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Calibration for Non-Exemplar Based Class-Incremental Learning.
Proceedings of the 2021 IEEE International Conference on Multimedia and Expo, 2021

Prototype Augmentation and Self-Supervision for Incremental Learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021


  Loading...