paper-with-me

Papers

LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models

2024-04-17 · Dingkun Zhang, Sijia Li, Chen Chen, Qingsong Xie, Haonan Lu

In the era of AIGC, the demand for low-budget or even on-device applications of diffusion models emerged. In terms of compressing the Stable Diffusion models (SDMs), several approaches have been proposed, and most of them leveraged the handcrafted layer removal methods to obtain smaller U-Nets, along with knowledge distillation to recover the network performance. However, such a handcrafting manner of layer removal is inefficient and lacks scalability and generalization, and the feature distillation employed in the retraining phase faces an imbalance issue that a few numerically significant feature loss terms dominate over others throughout the retraining process. To this end, we proposed the layer pruning and normalized distillation for compressing diffusion models (LAPTOP-Diff). We, 1) introduced the layer pruning method to compress SDM's U-Net automatically and proposed an effective one-shot pruning criterion whose one-shot performance is guaranteed by its good additivity property, surpassing other layer pruning and handcrafted layer removal methods, 2) proposed the normalized feature distillation for retraining, alleviated the imbalance issue. Using the proposed LAPTOP-Diff, we compressed the U-Nets of SDXL and SDM-v1.5 for the most advanced performance, achieving a minimal 4.0% decline in PickScore at a pruning ratio of 50% while the comparative methods' minimal PickScore decline is 8.2%. We will release our code.

📄 PDF Abstract BibTeX arXiv:2404.11098

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

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…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
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…
Pruning 설명 없음
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…
U-Net 설명 없음
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Structured Pruning Learns Compact and Accurate Models

2022-04-01 · ACL 2022 5 · Mengzhou Xia, Zexuan Zhong, Danqi Chen

The growing size of neural language models has led to increased attention in model compression. The two predominant approaches are pruning, which gradually removes weights from a pre-trained model, and distillation, whic…

Model Compression

Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers

2025-11-20 · Jian Ma, Qirong Peng, Xujie Zhu, Peixing Xie 외 arxiv

Diffusion Transformers (DiTs) have shown exceptional performance in image generation, yet their large parameter counts incur high computational costs, impeding deployment in resource-constrained settings. To address this…

Image Generation

Greedy-layer Pruning: Speeding up Transformer Models for Natural Language Processing

2021-05-31 · David Peer, Sebastian Stabinger, Stefan Engl, Antonio Rodriguez-Sanchez

Fine-tuning transformer models after unsupervised pre-training reaches a very high performance on many different natural language processing tasks. Unfortunately, transformers suffer from long inference times which great…

Knowledge DistillationUnsupervised Pre-training

Structured Pruning Learns Compact and Accurate Models

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

The growing size of neural language models has led to increased attention in model compression. Pruning methods start from a large model and gradually remove model weights---they can significantly reduce the model size b…

Model Compression

Class-Discriminative CNN Compression

2021-10-21 · Yuchen Liu, David Wentzlaff, S. Y. Kung

Compressing convolutional neural networks (CNNs) by pruning and distillation has received ever-increasing focus in the community. In particular, designing a class-discrimination based approach would be desired as it fits…