paper-with-me

Papers

Weak-to-Strong Knowledge Distillation Accelerates Visual Learning

2026-04-16 · Baiang Li, Wenhao Chai, Felix Heide arxiv

Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression or final-accuracy improvement. We instead investigate distillation to accelerate the training of strong students. We propose a generalizable plug-and-play recipe that freezes a weaker teacher, applies distillation only in early training, and turns it off once the student reaches and surpasses teacher-level performance. For ImageNet and CIFAR classification, this strategy reaches target thresholds much earlier, with up to 4.8 times speedup measured by epochs. We confirm that the method generalizes to other tasks and report 1.7 times epoch speedup for object detection on the COCO dataset, and 2.5 times earlier target-FID crossing for diffusion generation on the CIFAR-10 dataset, measured in steps. These findings validate our method as a universal speedup mechanism for visual learning.

📄 PDF Abstract BibTeX arXiv:2604.15451

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationObject Detection

Similar Papers 제목 키워드 기반

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

2026-09-08 · Youngrok Park, Sangmin Bae, Hojung Jung, Jongwoo Ko 외 hf

Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This question is particularly important for successive model generations and multi-domain consolidation, wher…

Strong Teacher Not Needed? On Distillation in LLM Pretraining

2026-05-22 · Taiming Lu, Zhuang Liu arxiv

Knowledge distillation generally assumes a strong-to-weak relationship where stronger teachers yield better students. In this work, we examine this assumption about distillation in large language model pretraining. By va…

Knowledge Distillation

Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers

2025-10-09 · Yongqi Ding, Lin Zuo, Mengmeng Jing, Kunshan Yang 외 arxiv

Brain-inspired spiking neural networks (SNNs) promise to be a low-power alternative to computationally intensive artificial neural networks (ANNs), although performance gaps persist. Recent studies have improved the perf…

Knowledge DistillationAdversarial Robustness

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight

2026-05-29 · Can Jin, Jiakang Li, Rui Wu, Eddy Zhang 외 arxiv

As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, limiting both weak-to-strong generalization and scalable oversight. We …

Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance

2023-12-07 · Thomas Westfechtel, Dexuan Zhang, Tatsuya Harada

Unsupervised domain adaptation (UDA) tries to overcome the tedious work of labeling data by leveraging a labeled source dataset and transferring its knowledge to a similar but different target dataset. Meanwhile, current…

Domain AdaptationKnowledge DistillationLanguage ModellingSelf-Knowledge Distillation+1