Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning

• URL: http://arxiv.org/abs/2411.06764v1
• Date: Mon, 11 Nov 2024 07:36:19 GMT
• Title: Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning
• Authors: Hongsheng Zhang, Zhong Ji, Jingren Liu, Yanwei Pang, Jungong Han,
• Abstract summary: We propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks.
• Score: 79.46570165281084
• License:
• Abstract: Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data distributions without joint training, but faces challenges of catastrophic forgetting and generalization forgetting. Although significant progress has been achieved by distillation-based methods, they exhibit two severe limitations. One is the popularly adopted single-teacher paradigm fails to impart comprehensive knowledge, The other is the existing methods inadequately leverage the multimodal information in the original training dataset, instead they rely on additional data for distillation, which increases computational and storage overhead. To mitigate both limitations, by drawing on Knowledge Integration Theory (KIT), we propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. During the four stages, we first leverage prototypes to align across modalities, eliciting cross-modal knowledge, then adding new knowledge by constructing fine-grained intra- and inter-modality relationships with prototypes. After that, knowledge from two teacher models is adaptively distinguished and re-weighted. Finally, we connect between models from intra- and inter-task, integrating preceding and new knowledge. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks, showcasing its potential in adapting VLMs to evolving data distributions.

Related papers

• ATLAS: Adapter-Based Multi-Modal Continual Learning with a Two-Stage Learning Strategy [12.150065431702055]
  We propose a multi-modal continual learning scheme that consists of experience-based learning and novel knowledge expansion. Our method is proficient for continual learning. It expands the distribution of representation upstream while also minimizing the negative impact of forgetting previous tasks.
  arXiv  Detail & Related papers  (2024-10-14T13:29:42Z)
• A Unified Framework for Continual Learning and Machine Unlearning [9.538733681436836]
  Continual learning and machine unlearning are crucial challenges in machine learning, typically addressed separately. We introduce a novel framework that jointly tackles both tasks by leveraging controlled knowledge distillation. Our approach enables efficient learning with minimal forgetting and effective targeted unlearning.
  arXiv  Detail & Related papers  (2024-08-21T06:49:59Z)
• Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models [79.28821338925947]
  Domain-Class Incremental Learning is a realistic but challenging continual learning scenario. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. This incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy overhead. We propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of
  arXiv  Detail & Related papers  (2024-07-07T12:19:37Z)
• Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters [65.15700861265432]
  We present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters. To preserve the zero-shot recognition capability of vision-language models, we introduce a Distribution Discriminative Auto-Selector.
  arXiv  Detail & Related papers  (2024-03-18T08:00:23Z)
• Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery [47.28191501836041]
  In this paper, we employ a Reinforcement Learning framework to simulate the cognitive processes of humans. We also deploy a Member-to-Leader Multi-Agent framework to extract and fuse features from multi-modal information. We demonstrate the performance of our approach in both the 3D and 2D domains by employing the OS-MN40, OS-MN40-Miss, and Cifar10 datasets.
  arXiv  Detail & Related papers  (2023-08-26T07:55:32Z)
• Multi-View Class Incremental Learning [57.14644913531313]
  Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. This paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), where a single model incrementally classifies new classes from a continual stream of views.
  arXiv  Detail & Related papers  (2023-06-16T08:13:41Z)
• Learning without Forgetting for Vision-Language Models [65.49600786387106]
  Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world. Recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations. We propose PROjectiOn Fusion (PROOF) that enables VLMs to learn without forgetting.
  arXiv  Detail & Related papers  (2023-05-30T17:59:32Z)
• A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training [73.7507857547549]
  We propose to unify knowledge discovery and multi-modal pre-training in a continuous learning framework. For knowledge discovery, a pre-trained model is used to identify cross-modal links on a graph. For model pre-training, the knowledge graph is used as the external knowledge to guide the model updating.
  arXiv  Detail & Related papers  (2022-06-11T16:05:06Z)

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.