Learning-Based Image Compression for Machines
This work addresses the need for compression pipelines that retain features for machine learning analysis, which is incremental as it builds on existing learning-based compression techniques.
The paper tackles the problem of learning-based image compression not being widely adopted in machine learning pipelines due to lack of standardization and retention of salient features for downstream tasks, by proposing methods to finetune and enhance pretrained compression pipelines to improve performance on vision tasks.
While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient features needed for such tasks. Decompression of images have taken a back seat in recent years while the focus has shifted to an image's utility in performing machine learning based analysis on top of them. Thus the demand for compression pipelines that incorporate such features from images has become ever present. The methods outlined in the report build on the recent work done on learning based image compression techniques to incorporate downstream tasks in them. We propose various methods of finetuning and enhancing different parts of pretrained compression encoding pipeline and present the results of our investigation regarding the performance of vision tasks using compression based pipelines.