paper-with-me

홈 › Papers

Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization

2017-07-28 · Frederick Tung, Srikanth Muralidharan, Greg Mori

When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual space than the source domain used for pre-training (e.g. ImageNet), the fine-tuned network is likely to be over-parameterized. However, applying network pruning as a post-processing step to reduce the memory requirements has drawbacks: fine-tuning and pruning are performed independently; pruning parameters are set once and cannot adapt over time; and the highly parameterized nature of state-of-the-art pruning methods make it prohibitive to manually search the pruning parameter space for deep networks, leading to coarse approximations. We propose a principled method for jointly fine-tuning and compressing a pre-trained convolutional network that overcomes these limitations. Experiments on two specialized image domains (remote sensing images and describable textures) demonstrate the validity of the proposed approach.

📄 PDF Abstract BibTeX arXiv:1707.09102

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian OptimizationNetwork Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference

2026-04-10 · Yueyuan Sui, Payal Mohapatra, Doğaç Eldenk, Haodong Yang 외 arxiv

Edge devices increasingly run multimodal sensing pipelines that must remain accurate despite fluctuating power budgets and unpredictable sensor dropout. Existing pruning methods fail under these conditions: they generall…

CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization

2018-06-01 · CVPR 2018 6 · Frederick Tung, Greg Mori

Deep neural networks enable state-of-the-art accuracy on visual recognition tasks such as image classification and object detection. However, modern deep networks contain millions of learned weights; a more efficient uti…

image-classificationImage ClassificationNetwork Pruningobject-detection+2

OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization

2022-05-23 · Peng Hu, Xi Peng, Hongyuan Zhu, Mohamed M. Sabry Aly 외

As Deep Neural Networks (DNNs) usually are overparameterized and have millions of weight parameters, it is challenging to deploy these large DNN models on resource-constrained hardware platforms, e.g., smartphones. Numer…

Quantization

Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression

2025-05-13 · Jacob Sander, David Moe, Achraf Cohen, Brent Venable 외

Modern foundational models are often compressed via a combination of structured pruning and re-training to meet the strict compute, memory, and connectivity constraints of edge deployments. While state-of-the-art pruning…

Just CHOP: Embarrassingly Simple LLM Compression

2023-05-24 · Ananya Harsh Jha, Tom Sherborne, Evan Pete Walsh, Dirk Groeneveld 외

Large language models (LLMs) enable unparalleled few- and zero-shot reasoning capabilities but at a high computational footprint. A growing assortment of methods for compression promises to reduce the computational burde…

Knowledge DistillationLanguage ModelingLanguage ModellingLarge Language Model+1