paper-with-me

홈 › Papers

PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification

2026-02-08 · Qiuming Luo, Yuebing Li, Feng Li, Chang Kong arxiv

Distilling knowledge from large Vision-Language Models (VLMs) into lightweight networks is crucial yet challenging in Fine-Grained Visual Classification (FGVC), due to the reliance on fixed prompts and global alignment. To address this, we propose PAND (Prompt-Aware Neighborhood Distillation), a two-stage framework that decouples semantic calibration from structural transfer. First, we incorporate Prompt-Aware Semantic Calibration to generate adaptive semantic anchors. Second, we introduce a neighborhood-aware structural distillation strategy to constrain the student's local decision structure. PAND consistently outperforms state-of-the-art methods on four FGVC benchmarks. Notably, our ResNet-18 student achieves 76.09% accuracy on CUB-200, surpassing the strong baseline VL2Lite by 3.4%. Code is available at https://github.com/LLLVTA/PAND.

📄 PDF Abstract BibTeX arXiv:2602.07768

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Locality-Aware Continual Unlearning for Diffusion Models

2025-12-02 · Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri 외 arxiv

Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time. Existing unlearning methods, however, are designed for single-s…

PANDO: Efficient Multimodal AI Agents via Online Skill Distillation

2026-05-24 · Yubo Li, Yidi Miao, Yuntian Shen, Yuxin Liu arxiv

Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist model stacks. This raises a central question…

A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation

2024-03-06 · Lirong Wu, Haitao Lin, Zhangyang Gao, Guojiang Zhao 외

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical…

Knowledge Distillation

Transferable Class Statistics and Multi-scale Feature Approximation for 3D Object Detection

2025-08-16 · Hao Peng, Hong Sang, Yajing Ma, Ping Qiu 외 arxiv

This paper investigates multi-scale feature approximation and transferable features for object detection from point clouds. Multi-scale features are critical for object detection from point clouds. However, multi-scale f…

Knowledge Distillation3D Object DetectionPoint Clouds

Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration

2024-09-05 · Pei Wang, Xiaotong Luo, Yuan Xie, Yanyun Qu

Multi-weather image restoration has witnessed incredible progress, while the increasing model capacity and expensive data acquisition impair its applications in memory-limited devices. Data-free distillation provides an …

Image RestorationKnowledge Distillation