Presentation | 2024-01-26 A Preliminary Study on Pre-training for Improved Explainability in End-to-End Driving Models Zhang Chenkai, Deguchi Daisuke, Chen Jialei, Murase Hiroshi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In the realm of autonomous driving, end-to-end models (E2EDMs) have gained prominence due to their high predictive accuracy. Such accuracy is attributed to the utilization of a backbone pre-trained on large datasets, subsequently fine-tuned on autonomous driving datasets. However, the inherent ``black box'' nature of these E2EDMs poses significant challenges in terms of explainability. Current methodologies predominantly focus on generating visual explanations for the E2EDMs' decision-making process. Numerous approaches aim to enhance the explainability of these E2EDMs by fine-tuning with complicated architectures, supplemented by additional information, e.g., object position to develop more explainable E2EDMs. In this study, we diverge from the conventional approaches where significant effort is placed during the fine-tuning phase of E2EDMs. Our method focuses on training backbones before the fine-tuning phase. This preemptive strategy enables us to fine-tune more explainable E2EDMs without the need for additional information or complex training techniques. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Explainability / autonomous vehicles / deep learning / convolutional neural networks |
Paper # | PRMU2023-48 |
Date of Issue | 2024-01-18 (PRMU) |
Conference Information | |
Committee | PRMU / MVE / VRSJ-SIG-MR / IPSJ-CVIM |
---|---|
Conference Date | 2024/1/25(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Keio Univ. (Hiyoshi Campus) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Kunio Kashio(NTT) / Kiyoshi Kiyokawa(NAIST) / / 日浦 慎作(兵庫県立大) |
Vice Chair | Takuya Funatomi(NAIST) / Go Irie(Tokyo Univ. of Science) / Sumaru Niida(KDDI Research) |
Secretary | Takuya Funatomi(Tokyo Inst. of Tech.) / Go Irie(Riken) / Sumaru Niida(Otsuma Women's University) / (DNP) / (Kyushu Univ.) |
Assistant | Kei Shimonishi(Kyoto Univ.) / Kensho Hara(AIST) / Hidehiko Shishido(Soka University) / Atsushi Nakazawa(Kyoto Univ.) / Naoya Tojo(KDDI Research) / Naoki Hagiyama(NTT) / Yuji Tatada(Univ. of Tokyo) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Media Experience and Virtual Environment / SIG-MR / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | ENG-JTITLE |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Preliminary Study on Pre-training for Improved Explainability in End-to-End Driving Models |
Sub Title (in English) | |
Keyword(1) | Explainability |
Keyword(2) | autonomous vehicles |
Keyword(3) | deep learning |
Keyword(4) | convolutional neural networks |
1st Author's Name | Zhang Chenkai |
1st Author's Affiliation | Nagoya University(Nagoya Univ) |
2nd Author's Name | Deguchi Daisuke |
2nd Author's Affiliation | Nagoya University(Nagoya Univ) |
3rd Author's Name | Chen Jialei |
3rd Author's Affiliation | Nagoya University(Nagoya Univ) |
4th Author's Name | Murase Hiroshi |
4th Author's Affiliation | Nagoya University(Nagoya Univ) |
Date | 2024-01-26 |
Paper # | PRMU2023-48 |
Volume (vol) | vol.123 |
Number (no) | PRMU-358 |
Page | pp.pp.46-49(PRMU), |
#Pages | 4 |
Date of Issue | 2024-01-18 (PRMU) |