paper-with-me

Papers

PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression

2022-03-16 · Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama

We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this end, we propose a gradually shrinking GAN (PPCD-GAN) by introducing progressive pruning residual block (PP-Res) and class-aware distillation. The PP-Res is an extension of the conventional residual block where each convolutional layer is followed by a learnable mask layer to progressively prune network parameters as training proceeds. The class-aware distillation, on the other hand, enhances the stability of training by transferring immense knowledge from a well-trained teacher model through instructive attention maps. We train the pruning and distillation processes simultaneously on a well-known GAN architecture in an end-to-end manner. After training, all redundant parameters as well as the mask layers are discarded, yielding a lighter network while retaining the performance. We comprehensively illustrate, on ImageNet 128x128 dataset, PPCD-GAN reduces up to 5.2x (81%) parameters against state-of-the-arts while keeping better performance.

📄 PDF Abstract BibTeX arXiv:2203.08456

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Network Compression

Methods 이 논문이 사용한 방법론

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…
Batch Normalization 설명 없음
Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

2021-10-15 · ACL 2022 5 · Shaoyi Huang, Dongkuan Xu, Ian E. H. Yen, Yijue Wang 외

Conventional wisdom in pruning Transformer-based language models is that pruning reduces the model expressiveness and thus is more likely to underfit rather than overfit. However, under the trending pretrain-and-finetune…

Knowledge Distillation

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Conventional wisdom in pruning Transformer-based language models is that pruning reduces the model expressiveness and thus is more likely to underfit rather than overfit. However, under the trending pretrain-and-finetune…

Knowledge Distillation

C2S2: Cost-aware Channel Sparse Selection for Progressive Network Pruning

2019-04-06 · Chih-Yao Chiu, Hwann-Tzong Chen, Tyng-Luh Liu

This paper describes a channel-selection approach for simplifying deep neural networks. Specifically, we propose a new type of generic network layer, called pruning layer, to seamlessly augment a given pre-trained model …

channel selectionimage-classificationImage ClassificationNetwork Pruning+1

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

2026-09-10 · Haojun Zhang, Yi Zou, Min Chen, Qize Yu 외 hf

Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks perturbs the embeddings consumed by the decoder and can cause deletion and premature end-of-sequence er…

PARE: Pruning and Adaptive Routing for Efficient Video Generation

2026-05-26 · Yutong Wang, Yunke Wang, Tianfan Xue, Yu Qiao 외 arxiv

Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. Recent methods reduce cost by compressing width, depth, or s…

Text-to-Video Generation