paper-with-me

홈 › Papers

All Centers Are at most a Few Tokens Apart: Knowledge Distillation with Domain Invariant Prompt Tuning

2025-11-27 · Amir Mohammad Ezzati, Alireza Malekhosseini, Armin Khosravi, Mohammad Hossein Rohban arxiv

Domain generalization is critical in computational pathology (CPath) due to inherent domain shifts caused by variations in staining protocols, scanner devices, and imaging settings across clinical centers. Vision-language models (VLMs), such as PLIP-a pathology-tuned CLIP-trained on image-text pairs across diverse domains, serve as strong knowledge distillation sources. However, their zero-shot performance with predefined prompts remains limited due to sensitivity to prompt variations. Moreover, unlike natural images, histopathology centers lack semantic descriptors (e.g., 'sketch'), making it difficult to define domain-specific prompts for clinical centers. This requires a data-driven approach for learning domain-specific and ultimately class-generic continuous prompts. We propose Domain Invariant Prompt Tuning (DIPT) for knowledge distillation process, a novel step that learns multiple input tokens for each domain. These tokens are trained separately for each domain and are averaged across domains, leading to domain-invariant prompts. Our student model then distills knowledge from PLIP's text encoder by leveraging the prompts learned by DIPT. This leads to alignment of visual features with domain-invariant embeddings, enhancing generalization by training on multiple domains. Our method adds a significant improvement in average F1-score to existing state-of-the-art (SOTA) knowledge distillation approaches in domain generalization with histopathology datasets. This work helps the way of deploying robust CPath models in real-world clinical problems with heterogeneous data sources.

📄 PDF Abstract BibTeX arXiv:2511.22739

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationDomain Generalization

Similar Papers 제목 키워드 기반

SRA: Span Representation Alignment for Large Language Model Distillation

2026-05-02 · Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi, Tung Nguyen 외 arxiv

Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While existing approaches mainly focus on token-l…

Knowledge Distillation

Tree Knowledge Distillation for Compressing Transformer-Based Language Models

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Knowledge distillation has emerged as a promising technique for compressing neural language models. However, most knowledge distillation methods focus on extracting the ``knowledge'' from a teacher network to guide the t…

Knowledge Distillation

LLM-Oriented Token-Adaptive Knowledge Distillation

2025-10-13 · Xurong Xie, Zhucun Xue, Jiafu Wu, Jian Li 외 arxiv

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning proce…

Knowledge Distillation

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation

2025-10-21 · Giovanni De Muri, Mark Vero, Robin Staab, Martin Vechev arxiv

LLMs are often used by downstream users as teacher models for knowledge distillation, compressing their capabilities into memory-efficient models. However, as these teacher models may stem from untrusted parties, distill…

Knowledge Distillation

On the Efficacy of Knowledge Distillation

2019-10-03 · ICCV 2019 10 · Jang Hyun Cho, Bharath Hariharan

In this paper, we present a thorough evaluation of the efficacy of knowledge distillation and its dependence on student and teacher architectures. Starting with the observation that more accurate teachers often don't mak…

Knowledge Distillation