research
∙
09/13/2023
PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
While traditional machine learning can effectively tackle a wide range o...
share
research
∙
07/14/2023
Streaming CTR Prediction: Rethinking Recommendation Task for Real-World Streaming Data
The Click-Through Rate (CTR) prediction task is critical in industrial r...
research
∙
05/30/2023
Learning without Forgetting for Vision-Language Models
Class-Incremental Learning (CIL) or continual learning is a desired capa...
research
∙
04/14/2023
Preserving Locality in Vision Transformers for Class Incremental Learning
Learning new classes without forgetting is crucial for real-world applic...
research
∙
03/13/2023
Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need
Class-incremental learning (CIL) aims to adapt to emerging new classes w...
research
∙
02/07/2023
Deep Class-Incremental Learning: A Survey
Deep models, e.g., CNNs and Vision Transformers, have achieved impressiv...
research
∙
05/26/2022
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
Real-world applications require the classification model to adapt to new...
research
∙
04/10/2022
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
The ability to learn new concepts continually is necessary in this ever-...
research
∙
03/31/2022
Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
New classes arise frequently in our ever-changing world, e.g., emerging ...
research
∙
03/14/2022
Forward Compatible Few-Shot Class-Incremental Learning
Novel classes frequently arise in our dynamically changing world, e.g., ...
research
∙
12/23/2021
PyCIL: A Python Toolbox for Class-Incremental Learning
Traditional machine learning systems are deployed under the closed-world...
research
∙
07/27/2021
Co-Transport for Class-Incremental Learning
Traditional learning systems are trained in closed-world for a fixed num...
research
∙
06/15/2021
Contextualizing Multiple Tasks via Learning to Decompose
One single instance could possess multiple portraits and reveal diverse ...
research
∙
03/28/2021