1 code implementation • 13 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.
1 code implementation • CVPR 2018 • Miguel Ã. Carreira-Perpiñán, Yerlan Idelbayev
Pruning a neural net consists of removing weights without degrading its performance.
no code implementations • 20 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.).
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.
1 code implementation • 15 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.
1 code implementation • CVPR 2020 • Yerlan Idelbayev, Miguel A. Carreira-Perpinan
Neural net compression can be achieved by approximating each layer's weight matrix by a low-rank matrix.
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.
1 code implementation • 9 Jul 2021 • Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev
However, VGG nets can be better compressed by combining low-rank with a few floating point weights.
no code implementations • 29 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.
no code implementations • 11 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, such as Stable Diffusion, to generate paired datasets used for training generative adversarial networks (GANs).
no code implementations • 27 Mar 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.