paper-with-me

홈 › Papers

Natural Statistics of Network Activations and Implications for Knowledge Distillation

2021-06-01 · Michael Rotman, Lior Wolf

In a matter that is analog to the study of natural image statistics, we study the natural statistics of the deep neural network activations at various layers. As we show, these statistics, similar to image statistics, follow a power law. We also show, both analytically and empirically, that with depth the exponent of this power law increases at a linear rate. As a direct implication of our discoveries, we present a method for performing Knowledge Distillation (KD). While classical KD methods consider the logits of the teacher network, more recent methods obtain a leap in performance by considering the activation maps. This, however, uses metrics that are suitable for comparing images. We propose to employ two additional loss terms that are based on the spectral properties of the intermediate activation maps. The proposed method obtains state of the art results on multiple image recognition KD benchmarks.

📄 PDF Abstract BibTeX arXiv:2106.00368

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

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.…

Similar Papers 제목 키워드 기반

A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics

2021-12-06 · Prasen Kumar Sharma, Arun Abraham, Vikram Nelvoy Rajendiran

Quantizing the floating-point weights and activations of deep convolutional neural networks to fixed-point representation yields reduced memory footprints and inference time. Recently, efforts have been afoot towards zer…

Quantization

Similarity-Preserving Knowledge Distillation

2019-07-23 · ICCV 2019 10 · Frederick Tung, Greg Mori

Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distil…

Knowledge DistillationNeural Network Compression

Knowledge distillation via adaptive instance normalization

2020-03-09 · Jing Yang, Brais Martinez, Adrian Bulat, Georgios Tzimiropoulos

This paper addresses the problem of model compression via knowledge distillation. To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean a…

Knowledge DistillationModel Compression

Knowledge Transfer with Jacobian Matching

2018-03-01 · ICML 2018 7 · Suraj Srinivas, Francois Fleuret

Classical distillation methods transfer representations from a "teacher" neural network to a "student" network by matching their output activations. Recent methods also match the Jacobians, or the gradient of output acti…

Transfer Learning

Gaussian-Based Pooling for Convolutional Neural Networks

2019-12-01 · NeurIPS 2019 12 · Takumi Kobayashi

Convolutional neural networks (CNNs) contain local pooling to effectively downsize feature maps for increasing computation efficiency as well as robustness to input variations. The local pooling methods are generally for…

image-classificationImage Classification