Optimizing JPEG Quantization for Classification Networks

by   Zhijing Li, et al.

Deep learning for computer vision depends on lossy image compression: it reduces the storage required for training and test data and lowers transfer costs in deployment. Mainstream datasets and imaging pipelines all rely on standard JPEG compression. In JPEG, the degree of quantization of frequency coefficients controls the lossiness: an 8 by 8 quantization table (Q-table) decides both the quality of the encoded image and the compression ratio. While a long history of work has sought better Q-tables, existing work either seeks to minimize image distortion or to optimize for models of the human visual system. This work asks whether JPEG Q-tables exist that are "better" for specific vision networks and can offer better quality–size trade-offs than ones designed for human perception or minimal distortion. We reconstruct an ImageNet test set with higher resolution to explore the effect of JPEG compression under novel Q-tables. We attempt several approaches to tune a Q-table for a vision task. We find that a simple sorted random sampling method can exceed the performance of the standard JPEG Q-table. We also use hyper-parameter tuning techniques including bounded random search, Bayesian optimization, and composite heuristic optimization methods. The new Q-tables we obtained can improve the compression rate by 10 fixed, or improve accuracy up to 2% at the same compression rate.


The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study

Handling digital images is almost always accompanied by a lossy compress...

Clustering Embedding Tables, Without First Learning Them

To work with categorical features, machine learning systems employ embed...

JQF: Optimal JPEG Quantization Table Fusion by Simulated Annealing on Texture Images and Predicting Textures

JPEG has been a widely used lossy image compression codec for nearly thr...

Modeling Image Quantization Tradeoffs for Optimal Compression

All Lossy compression algorithms employ similar compression schemes – fr...

Learning to Improve Image Compression without Changing the Standard Decoder

In recent years we have witnessed an increasing interest in applying Dee...

Practical applications of Set Shaping Theory in Huffman coding

One of the biggest criticisms of the Set Shaping Theory is the lack of a...

Simulated Annealing for JPEG Quantization

JPEG is one of the most widely used image formats, but in some ways rema...

Please sign up or login with your details

Forgot password? Click here to reset