Papers › Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression

Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression

6 Aug 2024arXiv:2408.03046archive 2025-07-28

Jonas Schmitt, Ruiping Liu, Junwei Zheng, Jiaming Zhang, Rainer Stiefelhagen

Lightweight and effective models are essential for devices with limited resources, such as intelligent vehicles. Structured pruning offers a promising approach to model compression and efficiency enhancement. However, existing methods often tie pruning techniques to specific model architectures or vision tasks. To address this limitation, we propose a novel unified pruning framework Comb, Prune, Distill (CPD), which addresses both model-agnostic and task-agnostic concerns simultaneously. Our framework employs a combing step to resolve hierarchical layer-wise dependency issues, enabling architecture independence. Additionally, the pruning pipeline adaptively remove parameters based on the importance scoring metrics regardless of vision tasks. To support the model in retaining its learned information, we introduce knowledge distillation during the pruning step. Extensive experiments demonstrate the generalizability of our framework, encompassing both convolutional neural network (CNN) and transformer models, as well as image classification and segmentation tasks. In image classification we achieve a speedup of up to x4.3 with a accuracy loss of 1.8% and in semantic segmentation up to x1.89 with a 5.1% loss in mIoU.

PaperPDFCode

Code

cranken/cpd 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 ClassificationKnowledge DistillationModel CompressionSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge DistillationPruning

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