mlsanityData to 7 Oct 2026

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

arXiv 2602.07768 ↗First posted 8 Feb 2026cs.CV cs.AI cs.LGcited by 0

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

Abstract (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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 18 of its 27 references that are in the map. First posted on arXiv 8 Feb 2026.

Builds on

18 of 27 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance21 Sep
  2. 2022Conditional Prompt Learning for Vision-Language Models10 Mar
  3. 2021Learning to Prompt for Vision-Language Models2 Sep

Other references · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  7. 2022A ConvNet for the 2020scited by 3,545
  8. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  9. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  10. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  11. 2019Relational Knowledge Distillationcited by 873
  12. 2022MaPLe: Multi-modal Prompt Learningcited by 685
3 more
  1. 2021Distilling Knowledge via Knowledge Reviewcited by 285
  2. 2023TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritancecited by 90
  3. 2023Visual In-Context Promptingcited by 52

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer
  2. 2025FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models Adaptation
  3. 2024Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models
  4. 2024Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models
  5. 2025Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
  6. 2026Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models
  7. 2026Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: From Evaluation to Diagnosis
  8. 2024Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation