CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
- URL: http://arxiv.org/abs/2403.10245v1
- Date: Fri, 15 Mar 2024 12:28:21 GMT
- Title: CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
- Authors: Yukun Li, Guansong Pang, Wei Suo, Chenchen Jing, Yuling Xi, Lingqiao Liu, Hao Chen, Guoqiang Liang, Peng Wang,
- Abstract summary: We introduce a novel approach, CoLeCLIP, that learns an open-domain CL model based on CLIP.
CoLeCLIP outperforms state-of-the-art methods for open-domain CL under both task- and class-incremental learning settings.
- Score: 38.063942750061585
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper explores the problem of continual learning (CL) of vision-language models (VLMs) in open domains, where the models need to perform continual updating and inference on a streaming of datasets from diverse seen and unseen domains with novel classes. Such a capability is crucial for various applications in open environments, e.g., AI assistants, autonomous driving systems, and robotics. Current CL studies mostly focus on closed-set scenarios in a single domain with known classes. Large pre-trained VLMs like CLIP have demonstrated superior zero-shot recognition ability, and a number of recent studies leverage this ability to mitigate catastrophic forgetting in CL, but they focus on closed-set CL in a single domain dataset. Open-domain CL of large VLMs is significantly more challenging due to 1) large class correlations and domain gaps across the datasets and 2) the forgetting of zero-shot knowledge in the pre-trained VLMs in addition to the knowledge learned from the newly adapted datasets. In this work we introduce a novel approach, termed CoLeCLIP, that learns an open-domain CL model based on CLIP. It addresses these challenges by a joint learning of a set of task prompts and a cross-domain class vocabulary. Extensive experiments on 11 domain datasets show that CoLeCLIP outperforms state-of-the-art methods for open-domain CL under both task- and class-incremental learning settings.
Related papers
- Slowing Down Forgetting in Continual Learning [20.57872238271025]
A common challenge in continual learning (CL) is forgetting, where the performance on old tasks drops after new, additional tasks are learned.
We propose a novel framework called ReCL to slow down forgetting in CL.
arXiv Detail & Related papers (2024-11-11T12:19:28Z) - Exploring Language Model Generalization in Low-Resource Extractive QA [57.14068405860034]
We investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift.
We devise a series of experiments to empirically explain the performance gap.
arXiv Detail & Related papers (2024-09-27T05:06:43Z) - Density Distribution-based Learning Framework for Addressing Online
Continual Learning Challenges [4.715630709185073]
We introduce a density distribution-based learning framework for online Continual Learning.
Our framework achieves superior average accuracy and time-space efficiency.
Our method outperforms popular CL approaches by a significant margin.
arXiv Detail & Related papers (2023-11-22T09:21:28Z) - AD-CLIP: Adapting Domains in Prompt Space Using CLIP [11.836764044083257]
We introduce textscAD-CLIP, a domain-agnostic prompt learning strategy for CLIP.
Our prompts are designed to be domain-invariant and class-generalizable, by conditioning prompt learning on image style and content features simultaneously.
Our experiments on three benchmark DA datasets demonstrate the effectiveness of textscAD-CLIP compared to existing literature.
arXiv Detail & Related papers (2023-08-10T15:58:28Z) - POP: Prompt Of Prompts for Continual Learning [59.15888651733645]
Continual learning (CL) aims to mimic the human ability to learn new concepts without catastrophic forgetting.
We show that a foundation model equipped with POP learning is able to outperform classic CL methods by a significant margin.
arXiv Detail & Related papers (2023-06-14T02:09:26Z) - CL-CrossVQA: A Continual Learning Benchmark for Cross-Domain Visual
Question Answering [31.983067109848342]
We introduce CL-CrossVQA, a rigorous Continual Learning benchmark for Cross-domain Visual Question Answering.
We conduct extensive experiments on 4 VLPMs, 4 CL approaches, and 5 VQA datasets from different domains.
arXiv Detail & Related papers (2022-11-19T02:43:30Z) - Beyond Supervised Continual Learning: a Review [69.9674326582747]
Continual Learning (CL) is a flavor of machine learning where the usual assumption of stationary data distribution is relaxed or omitted.
Changes in the data distribution can cause the so-called catastrophic forgetting (CF) effect: an abrupt loss of previous knowledge.
This article reviews literature that study CL in other settings, such as learning with reduced supervision, fully unsupervised learning, and reinforcement learning.
arXiv Detail & Related papers (2022-08-30T14:44:41Z) - The CLEAR Benchmark: Continual LEArning on Real-World Imagery [77.98377088698984]
Continual learning (CL) is widely regarded as crucial challenge for lifelong AI.
We introduce CLEAR, the first continual image classification benchmark dataset with a natural temporal evolution of visual concepts.
We find that a simple unsupervised pre-training step can already boost state-of-the-art CL algorithms.
arXiv Detail & Related papers (2022-01-17T09:09:09Z) - Curriculum Learning for Reinforcement Learning Domains: A Framework and
Survey [53.73359052511171]
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback.
We present a framework for curriculum learning (CL) in RL, and use it to survey and classify existing CL methods in terms of their assumptions, capabilities, and goals.
arXiv Detail & Related papers (2020-03-10T20:41:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.