paper-with-me

Papers

Memory-Efficient Prompt Tuning for Incremental Histopathology Classification

2024-01-22 · Yu Zhu, Kang Li, Lequan Yu, Pheng-Ann Heng

Recent studies have made remarkable progress in histopathology classification. Based on current successes, contemporary works proposed to further upgrade the model towards a more generalizable and robust direction through incrementally learning from the sequentially delivered domains. Unlike previous parameter isolation based approaches that usually demand massive computation resources during model updating, we present a memory-efficient prompt tuning framework to cultivate model generalization potential in economical memory cost. For each incoming domain, we reuse the existing parameters of the initial classification model and attach lightweight trainable prompts into it for customized tuning. Considering the domain heterogeneity, we perform decoupled prompt tuning, where we adopt a domain-specific prompt for each domain to independently investigate its distinctive characteristics, and one domain-invariant prompt shared across all domains to continually explore the common content embedding throughout time. All domain-specific prompts will be appended to the prompt bank and isolated from further changes to prevent forgetting the distinctive features of early-seen domains. While the domain-invariant prompt will be passed on and iteratively evolve by style-augmented prompt refining to improve model generalization capability over time. In specific, we construct a graph with existing prompts and build a style-augmented graph attention network to guide the domain-invariant prompt exploring the overlapped latent embedding among all delivered domains for more domain generic representations. We have extensively evaluated our framework with two histopathology tasks, i.e., breast cancer metastasis classification and epithelium-stroma tissue classification, where our approach yielded superior performance and memory efficiency over the competing methods.

📄 PDF Abstract BibTeX arXiv:2401.11674

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGraph Attention

Similar Papers 제목 키워드 기반

Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images

2025-03-13 · Md Mamunur Rahaman, Ewan K. A. Millar, Erik Meijering

Zero-shot learning holds tremendous potential for histopathology image analysis by enabling models to generalize to unseen classes without extensive labeled data. Recent advancements in vision-language models (VLMs) have…

Diagnosticimage-classificationImage Classificationzero-shot-classification+1

Remind of the Past: Incremental Learning with Analogical Prompts

2023-03-24 · Zhiheng Ma, Xiaopeng Hong, Beinan Liu, Yabin Wang 외

Although data-free incremental learning methods are memory-friendly, accurately estimating and counteracting representation shifts is challenging in the absence of historical data. This paper addresses this thorny proble…

Incremental Learning

Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning

2023-03-21 · Jingwei Zhang, Saarthak Kapse, Ke Ma, Prateek Prasanna 외

Whole slide image (WSI) classification is a critical task in computational pathology, requiring the processing of gigapixel-sized images, which is challenging for current deep-learning methods. Current state of the art m…

GPU

Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning

2022-07-03 · Jinze Li, Yan Bai, Yihang Lou, Xiongkun Linghu 외

Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old ones. The difficulties are that training on…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting

2025-03-26 · Hao Fu, Hanbin Zhao, Jiahua Dong, Chao Zhang 외

Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Class-Incremental Learning (MCIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. With…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1