Indexado en

Licencia y uso

Citaciones

Cited 4 times in

Cited 1 times in

Altmetrics

Grant support

This workwas supported in part by the National Natural Science Foundation of China under Grant 62171353 and Grant 62101409 and in part by the Fundamental Research Funds for the Central Universities under Grant JB190116. The work of Luis Herranz was supported by the Grant PID2021-128178OB-I00(Ministry of Science, Innovation and Universities (MICINN), Spain) and inpart by the Ramon y Cajal under Grant RYC2019-027020-I.

Análisis de autorías institucional

Compartir

Task-Switchable Pre-Processor for Image Compression for Multiple Machine Vision Tasks

Publicado en:IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY. 34 (7): 6416-6429 - 2024-07-01 34(7), DOI: 10.1109/TCSVT.2023.3348995

Autores: Yang, Mingyi; Yang, Fei; Murn, Luka; Blanch, Marc Gorriz; Sock, Juil; Wan, Shuai; Yang, Fuzheng; Herranz, Luis

Afiliaciones

Resumen

Visual content is increasingly being processed by machines for various automated content analysis tasks instead of being consumed by humans. Despite the existence of several compression methods tailored for machine tasks, few consider real-world scenarios with multiple tasks. In this paper, we aim to address this gap by proposing a task-switchable pre-processor that optimizes input images specifically for machine consumption prior to encoding by an off-the-shelf codec designed for human consumption. The proposed task-switchable pre-processor adeptly maintains relevant semantic information based on the specific characteristics of different downstream tasks, while effectively suppressing irrelevant information to reduce bitrate. To enhance the processing of semantic information for diverse tasks, we leverage pre-extracted semantic features to modulate the pixel-to-pixel mapping within the pre-processor. By switching between different modulations, multiple tasks can be seamlessly incorporated into the system. Extensive experiments demonstrate the practicality and simplicity of our approach. It significantly reduces the number of parameters required for handling multiple tasks while still delivering impressive performance. Our method showcases the potential to achieve efficient and effective compression for machine vision tasks, supporting the evolving demands of real-world applications.

Palabras clave