paper-with-me

Papers

Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs

2022-06-29 · Bo-Kyeong Kim, Shinkook Choi, Hancheol Park

Pruning effectively compresses overparameterized models. Despite the success of pruning methods for discriminative models, applying them for generative models has been relatively rarely approached. This study conducts structured pruning on U-Net generators of conditional GANs. A per-layer sensitivity analysis confirms that many unnecessary filters exist in the innermost layers near the bottleneck and can be substantially pruned. Based on this observation, we prune these filters from multiple inner layers or suggest alternative architectures by completely eliminating the layers. We evaluate our approach with Pix2Pix for image-to-image translation and Wav2Lip for speech-driven talking face generation. Our method outperforms global pruning baselines, demonstrating the importance of properly considering where to prune for U-Net generators.

📄 PDF Abstract BibTeX arXiv:2206.14658

Code (0)

등록된 구현이 없습니다.

Tasks

Face GenerationImage-to-Image TranslationSensitivityTalking Face GenerationTranslation

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Pruning 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Batch Normalization 설명 없음
Sigmoid Activation 설명 없음
PatchGAN 설명 없음

Similar Papers 제목 키워드 기반

Towards thinner convolutional neural networks through Gradually Global Pruning

2017-03-29 · Zhengtao Wang, Ce Zhu, Zhiqiang Xia, Qi Guo 외

Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices. Among many pruning granularities, neuron level pruning will r…

Network Pruning

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models

2025-01-25 · Zihuai Xu, Yang Xu, Hongli Xu, Yunming Liao 외

Considering the hardware-friendly characteristics and broad applicability, structured pruning has emerged as an efficient solution to reduce the resource demands of large language models (LLMs) on resource-constrained de…

Efficient Token Pruning for LLaDA-V

2026-01-28 · Zhewen Wan, Tianchen Song, Chen Lin, Zhiyong Zhao 외 arxiv

Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style it…

StructPrune: Structured Global Pruning asymptotics with $\mathcal{O}(\sqrt{N})$ GPU Memory

2025-09-25 · Xinyuan Song, Guangji Bai, Liang Zhao arxiv

Pruning is critical for scaling large language models (LLMs). Global pruning achieves strong performance but requires $\mathcal{O}(N)$ memory, which is infeasible for billion-parameter models. Local pruning reduces GPU m…

POP: Prefill-Only Pruning for Efficient Large Model Inference

2026-02-03 · Junhui He, Zhihui Fu, Jun Wang, Qingan Li arxiv

Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities. However, their deployment is hindered by significant computational costs. Existing structured pruning methods, whi…