LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation
LEAP introduces a training curriculum for Vision Transformer feature-based knowledge distillation that uses the teacher’s intermediate feature maps as progressively harder targets, enabling the student to build a foundation before tackling higher-level abstractions. It achieves significant accuracy gains and training efficiency improvements across multiple benchmarks.
[2606.19483] LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation
[Submitted on 17 Jun 2026]
Title:LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation
View a PDF of the paper titled LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation, by Jiaqi Zhang and 5 other authors
View PDF HTML (experimental)
Abstract:Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentation. The immense computational requirements of backbones often necessitate distillation into smaller architectures for edge deployment. Feature-based knowledge distillation (KD) often suffers from the teacher-student gap; the student struggles to imitate teacher's complex feature map due to its limited capacity. To mitigate this bottleneck, we propose LEAP: Layer-skipping Efficiency via Adaptive Progression, a training curriculum for ViT feature-based knowledge distillation. By utilizing the teacher's intermediate feature maps as a sequence of progressively more difficult targets, our curriculum allows the student to build a foundational representation before tackling higher-level abstractions. Our results demonstrate that this paradigm significantly accelerates convergence through adaptive difficulty selection across various student model sizes and dataset scales. With our curriculum, the LEAP-distilled ViT-S achieves 90.1% accuracy on ImageNet-100, a +12.24% improvement compared with baseline. On ImageNet-1K, LEAP achieves +3.84% and +7.75% improvement for the instance retrieval task on the Oxford and Paris datasets, respectively. Furthermore, the curriculum enables 25.1% savings in training FLOPs and 21% savings in training time on ImageNet-100 by implementing early-stopping for teacher inference during the initial stages of training. Code is available at this https URL
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2606.19483 [cs.CV]
(or arXiv:2606.19483v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.19483
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Jiaqi Zhang [view email] [v1] Wed, 17 Jun 2026 18:14:51 UTC (521 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation, by Jiaqi Zhang and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)