paper-with-me

Papers

Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning

2024-01-03 · Zitong Huang, Ze Chen, Zhixing Chen, Erjin Zhou, Xinxing Xu, Rick Siow Mong Goh, Yong liu, WangMeng Zuo, ChunMei Feng

Few-shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes based on very limited training data without forgetting the old ones encountered. Existing studies solely relied on pure visual networks, while in this paper we solved FSCIL by leveraging the Vision-Language model (e.g., CLIP) and propose a simple yet effective framework, named Learning Prompt with Distribution-based Feature Replay (LP-DiF). We observe that simply using CLIP for zero-shot evaluation can substantially outperform the most influential methods. Then, prompt tuning technique is involved to further improve its adaptation ability, allowing the model to continually capture specific knowledge from each session. To prevent the learnable prompt from forgetting old knowledge in the new session, we propose a pseudo-feature replay approach. Specifically, we preserve the old knowledge of each class by maintaining a feature-level Gaussian distribution with a diagonal covariance matrix, which is estimated by the image features of training images and synthesized features generated from a VAE. When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge while retaining old knowledge. Experiments on three prevalent benchmarks, i.e., CIFAR100, mini-ImageNet, CUB-200, and two more challenging benchmarks, i.e., SUN-397 and CUB-200$^*$ proposed in this paper showcase the superiority of LP-DiF, achieving new state-of-the-art (SOTA) in FSCIL. Code is publicly available at https://github.com/1170300714/LP-DiF.

📄 PDF Abstract BibTeX arXiv:2401.01598

Code (1)

1170300714/lp-dif 공식 구현 pytorch

Tasks

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningLanguage Modelling

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning

2024-07-22 · Emanuele Frascaroli, Aniello Panariello, Pietro Buzzega, Lorenzo Bonicelli 외

With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of n…

Class Incremental LearningContinual LearningIncremental LearningPrompt Learning

GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer

2026-02-03 · Junmo Cho, Suhan Kim, Sangjune An, Minsu Kim 외 arxiv

Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based promp…

Few-Shot Text ClassificationQuestion Answering

LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning

2023-06-02 · NeurIPS 2023 11 · Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa

We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection. Few-shot OOD detection aims to detect OOD images from classes that are unseen during training using only a few…

Out-of-Distribution DetectionOut of Distribution (OOD) DetectionPrompt Learning

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

2023-03-12 · ICCV 2023 1 · Zangwei Zheng, Mingyuan Ma, Kai Wang, Ziheng Qin 외

Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the continual training of the Contrastive Languag…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning

Dynamic VAEs with Generative Replay for Continual Zero-shot Learning

2021-04-26 · Subhankar Ghosh

Continual zero-shot learning(CZSL) is a new domain to classify objects sequentially the model has not seen during training. It is more suitable than zero-shot and continual learning approaches in real-case scenarios when…

Continual LearningZero-Shot Learning