Search Results for author: Yerlan Idelbayev

Found 13 papers, 6 papers with code

Efficient Training with Denoised Neural Weights

no code implementations16 Jul 2024 Yifan Gong, Zheng Zhan, Yanyu Li, Yerlan Idelbayev, Andrey Zharkov, Kfir Aberman, Sergey Tulyakov, Yanzhi Wang, Jian Ren

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model.

Image-to-Image Translation Translation

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

1 code implementation6 Jun 2024 Yang Sui, Yanyu Li, Anil Kag, Yerlan Idelbayev, Junli Cao, Ju Hu, Dhritiman Sagar, Bo Yuan, Sergey Tulyakov, Jian Ren

Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content.

Image Generation Quantization

TextCraftor: Your Text Encoder Can be Image Quality Controller

no code implementations CVPR 2024 Yanyu Li, Xian Liu, Anil Kag, Ju Hu, Yerlan Idelbayev, Dhritiman Sagar, Yanzhi Wang, Sergey Tulyakov, Jian Ren

Our findings reveal that, instead of replacing the CLIP text encoder used in Stable Diffusion with other large language models, we can enhance it through our proposed fine-tuning approach, TextCraftor, leading to substantial improvements in quantitative benchmarks and human assessments.

Image Generation

E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation

no code implementations11 Jan 2024 Yifan Gong, Zheng Zhan, Qing Jin, Yanyu Li, Yerlan Idelbayev, Xian Liu, Andrey Zharkov, Kfir Aberman, Sergey Tulyakov, Yanzhi Wang, Jian Ren

One highly promising direction for enabling flexible real-time on-device image editing is utilizing data distillation by leveraging large-scale text-to-image diffusion models to generate paired datasets used for training generative adversarial networks (GANs).

Image-to-Image Translation

Faster Neural Net Inference via Forests of Sparse Oblique Decision Trees

no code implementations29 Sep 2021 Yerlan Idelbayev, Arman Zharmagambetov, Magzhan Gabidolla, Miguel A. Carreira-Perpinan

We show that neural nets can be further compressed by replacing layers of it with a special type of decision forest.

Quantization

Optimal Quantization Using Scaled Codebook

no code implementations CVPR 2021 Yerlan Idelbayev, Pavlo Molchanov, Maying Shen, Hongxu Yin, Miguel A. Carreira-Perpinan, Jose M. Alvarez

We study the problem of quantizing N sorted, scalar datapoints with a fixed codebook containing K entries that are allowed to be rescaled.

Quantization

A flexible, extensible software framework for model compression based on the LC algorithm

1 code implementation15 May 2020 Yerlan Idelbayev, Miguel Á. Carreira-Perpiñán

We propose a software framework based on the ideas of the Learning-Compression (LC) algorithm, that allows a user to compress a neural network or other machine learning model using different compression schemes with minimal effort.

BIG-bench Machine Learning Low-rank compression +3

Structured Multi-Hashing for Model Compression

no code implementations CVPR 2020 Elad Eban, Yair Movshovitz-Attias, Hao Wu, Mark Sandler, Andrew Poon, Yerlan Idelbayev, Miguel A. Carreira-Perpinan

Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory.

Model Compression

A Flexible, Extensible Software Framework for Neural Net Compression

no code implementations20 Oct 2018 Yerlan Idelbayev, Miguel Carreira-Perpinan

We propose a software framework based on ideas of the Learning-Compression algorithm , that allows one to compress any neural network by different compression mechanisms (pruning, quantization, low-rank, etc.).

Quantization

Model compression as constrained optimization, with application to neural nets. Part II: quantization

1 code implementation13 Jul 2017 Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev

We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.

Binarization Model Compression +1

Cannot find the paper you are looking for? You can Submit a new open access paper.