High-Efficiency Convolutional Ternary Neural Networks with Custom Adder Trees and Weight Compression
نویسندگان
چکیده
منابع مشابه
Compression Artifacts Removal Using Convolutional Neural Networks
This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously used smaller networks as well as to any other state-of-the-art methods. We were able to train networks with 8 layers in a single step and in relatively shor...
متن کاملMixed-Resolution Image Representation and Compression with Convolutional Neural Networks
In this paper, we propose a end-to-end mixed-resolution image compression framework with convolutional neural networks. Firstly, given one input image, feature description neural network (FDNN) is used to generate a new representation of this image, so that this image representation can be more efficiently compressed by standard coder, as compared to the input image. Furthermore, we use postpro...
متن کاملInterpreting Convolutional Neural Networks Through Compression
Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning filters in the interpretation of CNNs. We exploit our recently-proposed greedy s...
متن کاملDynamic Weight Alignment for Convolutional Neural Networks
In this paper, we propose a method of improving Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNNs convolve learnable shared weights, or filters, across the input data. The filters use a linear matching of weights to inputs using an inner product between the filter and a window of the input. However, it is ...
متن کاملTarget-Quality Image Compression with Recurrent, Convolutional Neural Networks
We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas. These methods lead to lower true bitrates for a given recursion count, both preand ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Transactions on Reconfigurable Technology and Systems
سال: 2018
ISSN: 1936-7406,1936-7414
DOI: 10.1145/3270764