Papers › VkD: Improving Knowledge Distillation using Orthogonal Projections

VkD: Improving Knowledge Distillation using Orthogonal Projections

1 Jan 2024CVPR 2024 1archive 2025-07-28

Roy Miles, Ismail Elezi, Jiankang Deng

Knowledge distillation is an effective method for training small and efficient deep learning models. However the efficacy of a single method can degenerate when transferring to other tasks modalities or even other architectures. To address this limitation we propose a novel constrained feature distillation method. This method is derived from a small set of core principles which results in two emerging components: an orthogonal projection and a task-specific normalisation. Equipped with both of these components our transformer models can outperform all previous methods on ImageNet and reach up to a 4.4% relative improvement over the previous state-of-the-art methods. To further demonstrate the generality of our method we apply it to object detection and image generation whereby we obtain consistent and substantial performance improvements over state-of-the-art. Code and models are publicly available.

PaperPDFCode

Code

roymiles/vkd officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image GenerationKnowledge DistillationObject Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge DistillationSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections