From 88368d6797ee8c8e24d9d712212eda66d8ed1513 Mon Sep 17 00:00:00 2001 From: Shijie Ma Date: Thu, 10 Oct 2024 16:14:07 +0800 Subject: [PATCH 1/2] Update README.md include our NeurIPS 2024 paper of continual generalized category discovery --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index e0856a1..f5682c9 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# Awesome-Novel-Class-Discovery +![image](https://github.com/user-attachments/assets/f9ede721-e7c8-4952-8dff-0e2a0b2979e4)![image](https://github.com/user-attachments/assets/741599e9-9d5f-44de-94f0-081f4ae3f5dd)# Awesome-Novel-Class-Discovery Novel Class Discovery (NCD) is a machine learning problem, where novel categories of instances are to be automatically discovered from an unlabelled pool. In contrast to clustering, NCD setting has access to labelled data from a disjoint set of classes. This topic has plausible real-world applications and is gathering much attention in the research community. @@ -49,6 +49,7 @@ Here, we provide a non-exhaustive list of papers that study NCD. ## 2024 +- Happy: A Debiased Learning Framework for Continual Generalized Category Discovery (**NeurIPS** 2024) [[paper]](https://arxiv.org/abs/2410.06535) [[code]](https://github.com/mashijie1028/Happy-CGCD) - Online Continuous Generalized Category Discovery (**ECCV** 2024) [[paper]](https://arxiv.org/abs/2408.13492) [[code]](https://github.com/KHU-AGI/OCGCD) - PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery (**ECCV** 2024) [[paper]](https://arxiv.org/abs/2407.19001) [[code]](https://github.com/Visual-AI/PromptCCD) - Self-Cooperation Knowledge Distillation for Novel Class Discovery (**ECCV** 2024) [[paper]](https://arxiv.org/abs/2407.01930) From 120963bed6a73849ca7613bdb2d35a2143a23488 Mon Sep 17 00:00:00 2001 From: Shijie Ma Date: Thu, 10 Oct 2024 16:15:40 +0800 Subject: [PATCH 2/2] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index f5682c9..d11f869 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -![image](https://github.com/user-attachments/assets/f9ede721-e7c8-4952-8dff-0e2a0b2979e4)![image](https://github.com/user-attachments/assets/741599e9-9d5f-44de-94f0-081f4ae3f5dd)# Awesome-Novel-Class-Discovery +# Awesome-Novel-Class-Discovery Novel Class Discovery (NCD) is a machine learning problem, where novel categories of instances are to be automatically discovered from an unlabelled pool. In contrast to clustering, NCD setting has access to labelled data from a disjoint set of classes. This topic has plausible real-world applications and is gathering much attention in the research community.