Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion

• URL: http://arxiv.org/abs/2407.14143v1
• Date: Fri, 19 Jul 2024 09:20:33 GMT
• Title: Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion
• Authors: Linlan Huang, Xusheng Cao, Haori Lu, Xialei Liu,
• Abstract summary: Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they demonstrate good generalization ability. However, further adaptation to downstream tasks by simply fine-tuning the model leads to severe forgetting. Most existing works with pre-trained models assume that the forgetting of old classes is uniform when the model acquires new knowledge.
• Score: 10.322832012497722
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they demonstrate good generalization ability that allows them to excel in class-incremental learning with completely frozen parameters. However, further adaptation to downstream tasks by simply fine-tuning the model leads to severe forgetting. Most existing works with pre-trained models assume that the forgetting of old classes is uniform when the model acquires new knowledge. In this paper, we propose a method named Adaptive Representation Adjustment and Parameter Fusion (RAPF). During training for new data, we measure the influence of new classes on old ones and adjust the representations, using textual features. After training, we employ a decomposed parameter fusion to further mitigate forgetting during adapter module fine-tuning. Experiments on several conventional benchmarks show that our method achieves state-of-the-art results. Our code is available at \url{https://github.com/linlany/RAPF}.

Related papers

• LoRA Unlearns More and Retains More (Student Abstract) [0.0]
  PruneLoRA reduces the need for large-scale parameter updates by applying low-rank updates to the model. We leverage LoRA to selectively modify a subset of the pruned model's parameters, thereby reducing the computational cost, memory requirements and improving the model's ability to retain performance on the remaining classes.
  arXiv  Detail & Related papers  (2024-11-16T16:47:57Z)
• Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning [55.384428765798496]
  New data exhibits a long-tailed distribution, such as e-commerce platform reviews. This necessitates continuous model learning imbalanced data without forgetting. We introduce AdaPtive Adapter RouTing (APART) as an exemplar-free solution for LTCIL.
  arXiv  Detail & Related papers  (2024-09-11T17:52:00Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer [44.10678347943115]
  Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. In this paper, we revisit different parameter-efficient tuning (PET) methods within the context of continual learning. We observe that adapter tuning demonstrates superiority over prompt-based methods, even without parameter expansion in each learning session.
  arXiv  Detail & Related papers  (2024-03-29T05:23:12Z)
• Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning [65.57123249246358]
  We propose ExpAndable Subspace Ensemble (EASE) for PTM-based CIL. We train a distinct lightweight adapter module for each new task, aiming to create task-specific subspaces. Our prototype complement strategy synthesizes old classes' new features without using any old class instance.
  arXiv  Detail & Related papers  (2024-03-18T17:58:13Z)
• 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)
• Class Incremental Learning with Pre-trained Vision-Language Models [59.15538370859431]
  We propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that enables further adaptation. Experiments on several conventional benchmarks consistently show a significant margin of improvement over the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-10-31T10:45:03Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift [27.806085423595334]
  We introduce LIMES, a new method for learning with non-stationary streaming data. We learn a single set of model parameters from which a specific classifier for any specific data distribution is derived. Experiments on a set of exemplary tasks using Twitter data show that LIMES achieves higher accuracy than alternative approaches.
  arXiv  Detail & Related papers  (2022-06-10T15:19:52Z)
• Few-Shot Lifelong Learning [35.05196800623617]
  Few-Shot Lifelong Learning enables deep learning models to perform lifelong/continual learning on few-shot data. Our method selects very few parameters from the model for training every new set of classes instead of training the full model. We experimentally show that our method significantly outperforms existing methods on the miniImageNet, CIFAR-100, and CUB-200 datasets.
  arXiv  Detail & Related papers  (2021-03-01T13:26:57Z)

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.