paper-with-me

Papers

Image Coding for Machines with Edge Information Learning Using Segment Anything

2024-03-07 · Takahiro Shindo, Kein Yamada, Taiju Watanabe, Hiroshi Watanabe

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.

📄 PDF Abstract BibTeX arXiv:2403.04173

Code (2)

final-0/sa-icm 공식 구현 pytorch
final-0/icm-v1 pytorch

Tasks

Image CompressionVideo Compression

Similar Papers 제목 키워드 기반

Rate-Distortion Theory in Coding for Machines and its Application

2023-05-26 · Alon Harell, Yalda Foroutan, Nilesh Ahuja, Parual Datta 외

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 Segmentation

Conditional and Residual Methods in Scalable Coding for Humans and Machines

2023-05-04 · Anderson de Andrade, Alon Harell, Yalda Foroutan, Ivan V. Bajić

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 Segmentation

Evaluation of Video Coding for Machines without Ground Truth

2022-05-13 · Kristian Fischer, Markus Hofbauer, Christopher Kuhn, Eckehard Steinbach 외

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+1

Image coding for machines: an end-to-end learned approach

2021-08-23 · Nam Le, Honglei Zhang, Francesco Cricri, Ramin Ghaznavi-Youvalari 외

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 Segmentation

PAT-VCM: Plug-and-Play Auxiliary Tokens for Video Coding for Machines

2026-04-14 · Wei Jiang, Wei Wang arxiv

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