Image Coding for Machines with Edge Information Learning Using Segment Anything
Image Coding for Machines (ICM) is an image compression technique for image recognition. This technique is essential due to the growing demand for image recognition AI. In this paper, we propose a method for ICM that focuses on encoding and decoding only the edge information of object parts in an image, which we call SA-ICM. This is an Learned Image Compression (LIC) model trained using edge information created by Segment Anything. Our method can be used for image recognition models with various tasks. SA-ICM is also robust to changes in input data, making it effective for a variety of use cases. Additionally, our method provides benefits from a privacy point of view, as it removes human facial information on the encoder's side, thus protecting one's privacy. Furthermore, this LIC model training method can be used to train Neural Representations for Videos (NeRV), which is a video compression model. By training NeRV using edge information created by Segment Anything, it is possible to create a NeRV that is effective for image recognition (SA-NeRV). Experimental results confirm the advantages of SA-ICM, presenting the best performance in image compression for image recognition. We also show that SA-NeRV is superior to ordinary NeRV in video compression for machines. Code is available at https://github.com/final-0/SA-ICM.
Code (2)
Tasks
Image CompressionVideo CompressionSimilar Papers 제목 키워드 기반
Rate-Distortion Theory in Coding for Machines and its Application
Recent years have seen a tremendous growth in both the capability and popularity of automatic machine analysis of images and video. As a result, a growing need for efficient compression methods optimized for machine visi…
Instance Segmentationobject-detectionObject DetectionSemantic SegmentationConditional and Residual Methods in Scalable Coding for Humans and Machines
We present methods for conditional and residual coding in the context of scalable coding for humans and machines. Our focus is on optimizing the rate-distortion performance of the reconstruction task using the informatio…
Image Reconstructionobject-detectionObject DetectionSemantic SegmentationEvaluation of Video Coding for Machines without Ground Truth
In the emerging field of video coding for machines, video datasets with pristine video quality and high-quality annotations are required for a comprehensive evaluation. However, existing video datasets with detailed anno…
Instance Segmentationobject-detectionObject DetectionSegmentation+1Image coding for machines: an end-to-end learned approach
Over recent years, deep learning-based computer vision systems have been applied to images at an ever-increasing pace, oftentimes representing the only type of consumption for those images. Given the dramatic explosion i…
Instance Segmentationobject-detectionObject DetectionSemantic SegmentationPAT-VCM: Plug-and-Play Auxiliary Tokens for Video Coding for Machines
Existing video coding for machines is often trained for a specific downstream task and model. As a result, the compressed representation becomes tightly coupled to the end task, making it difficult to scale across multip…
Depth Estimation