Exploring Effective Knowledge Distillation for Tiny Object Detection
Liu, Haotian; Liu, Qing; Liu, Yang; Liang, Yixiong; Zhao, Guoying (2023-09-11)
IEEE
11.09.2023
H. Liu, Q. Liu, Y. Liu, Y. Liang and G. Zhao, "Exploring Effective Knowledge Distillation for Tiny Object Detection," 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia, 2023, pp. 770-774, doi: 10.1109/ICIP49359.2023.10222589.
https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202312123670
https://urn.fi/URN:NBN:fi:oulu-202312123670
Tiivistelmä
Abstract
Detecting tiny objects is a long-standing and critical problem in object detection, with broad real-world applications such as autonomous driving, surveillance, and medical diagnosis. Recent studies for tiny object detection often cause extra computational costs during inference due to introducing feature maps with increased resolution or additional network modules. This scarifies the inference speed for better detection accuracy and may heavily limit their availability to real-world applications. Therefore, this paper turns to knowledge distillation to improve the representation learning of a small model regarding both superior detection accuracy and fast inference speed. The masked scale-aware feature distillation and local attention distillation are proposed to address the critical issues in the distillation of tiny objects. Experimental results on two tiny benchmarks indicate that our method can bring noticeable performance gains to different detectors while keeping their original inference speeds. Our method also shows competitive performance compared to state-of-the-art methods for tiny object detection. Our code is available at https://github.com/haotianll/TinyKD.
Detecting tiny objects is a long-standing and critical problem in object detection, with broad real-world applications such as autonomous driving, surveillance, and medical diagnosis. Recent studies for tiny object detection often cause extra computational costs during inference due to introducing feature maps with increased resolution or additional network modules. This scarifies the inference speed for better detection accuracy and may heavily limit their availability to real-world applications. Therefore, this paper turns to knowledge distillation to improve the representation learning of a small model regarding both superior detection accuracy and fast inference speed. The masked scale-aware feature distillation and local attention distillation are proposed to address the critical issues in the distillation of tiny objects. Experimental results on two tiny benchmarks indicate that our method can bring noticeable performance gains to different detectors while keeping their original inference speeds. Our method also shows competitive performance compared to state-of-the-art methods for tiny object detection. Our code is available at https://github.com/haotianll/TinyKD.
Kokoelmat
- Avoin saatavuus [38840]