Comments (1)
Task-incremental learning often refers to classification tasks, such as learning from Birds -> Flowers -> Cars, which is quite popular from the very beginning, there are several papers in this rep working on this setting.
Also I worked on Task-incremental learning on object detection: feel free to check this paper, but this is rarely explored.
What you propose is quite interesting if I understood correctly. One example could be learning from depth estimation -> segmentation -> Surface Normal in NYU-v2 dataset. This could be also tested on much larger multi-task dataset, such as [Taskonomy: Disentangling Task Transfer Learning]. However, I haven't noticed work on this setting.
from awesome-incremental-learning.
Related Issues (20)
- Considering recommender system paper HOT 1
- Considering our NeurIPS 22 and CVPR 23 class incremental learning series HOT 1
- Add CVPR2023 paper HOT 1
- Add ICCV 2023 works
- Add ICCV 2023 Paper
- Add ICCV 2023 Paper HOT 1
- Request to add published long survey article and two other published works HOT 1
- Added code for NeurIPS 2023 paper. HOT 1
- Add AAAI 2024 Paper HOT 1
- Add ICCV workshop paper
- Add ICCV 2023 paper HOT 1
- Please add 'MIND: Multi-Task Incremental Network Distillation' accepted at AAAI 2024 HOT 1
- Consider Adding PR paper
- Suggestion to add a survey paper comparing replay for continual learning in the brain and AI HOT 1
- WACV 2022 Papers are missing HOT 3
- how about adding gaenari(c++ incremental decision tree)?
- Considering the ICML2022 paper HOT 2
- Recommend to use this tool to search continual-related papers
- Considering the COLING'22 paper HOT 1
- Are there any incremental learning papers that do not use the old task data? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from awesome-incremental-learning.