One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916660122746880 |
|---|---|
| author | Xia, Yuchen Yuan, Quan Luo, Guiyang Fu, Xiaoyuan Li, Yang Zhu, Xuanhan Luo, Tianyou Chen, Siheng Li, Jinglin |
| author_facet | Xia, Yuchen Yuan, Quan Luo, Guiyang Fu, Xiaoyuan Li, Yang Zhu, Xuanhan Luo, Tianyou Chen, Siheng Li, Jinglin |
| contents | Collaborative perception in autonomous driving significantly enhances the perception capabilities of individual agents. Immutable heterogeneity, where agents have different and fixed perception networks, presents a major challenge due to the semantic gap in exchanged intermediate features without modifying the perception networks. Most existing methods bridge the semantic gap through interpreters. However, they either require training a new interpreter for each new agent type, limiting extensibility, or rely on a two-stage interpretation via an intermediate standardized semantic space, causing cumulative semantic loss. To achieve both extensibility in immutable heterogeneous scenarios and low-loss feature interpretation, we propose PolyInter, a polymorphic feature interpreter. It provides an extension point where new agents integrate by overriding only their specific prompts, which are learnable parameters that guide interpretation, while reusing PolyInter's remaining parameters. By leveraging polymorphism, our design enables a single interpreter to accommodate diverse agents and interpret their features into the ego agent's semantic space. Experiments on the OPV2V dataset demonstrate that PolyInter improves collaborative perception precision by up to 11.1% compared to SOTA interpreters, while comparable results can be achieved by training only 1.4% of PolyInter's parameters when adapting to new agents. Code is available at https://github.com/yuchen-xia/PolyInter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16799 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception Xia, Yuchen Yuan, Quan Luo, Guiyang Fu, Xiaoyuan Li, Yang Zhu, Xuanhan Luo, Tianyou Chen, Siheng Li, Jinglin Computer Vision and Pattern Recognition Collaborative perception in autonomous driving significantly enhances the perception capabilities of individual agents. Immutable heterogeneity, where agents have different and fixed perception networks, presents a major challenge due to the semantic gap in exchanged intermediate features without modifying the perception networks. Most existing methods bridge the semantic gap through interpreters. However, they either require training a new interpreter for each new agent type, limiting extensibility, or rely on a two-stage interpretation via an intermediate standardized semantic space, causing cumulative semantic loss. To achieve both extensibility in immutable heterogeneous scenarios and low-loss feature interpretation, we propose PolyInter, a polymorphic feature interpreter. It provides an extension point where new agents integrate by overriding only their specific prompts, which are learnable parameters that guide interpretation, while reusing PolyInter's remaining parameters. By leveraging polymorphism, our design enables a single interpreter to accommodate diverse agents and interpret their features into the ego agent's semantic space. Experiments on the OPV2V dataset demonstrate that PolyInter improves collaborative perception precision by up to 11.1% compared to SOTA interpreters, while comparable results can be achieved by training only 1.4% of PolyInter's parameters when adapting to new agents. Code is available at https://github.com/yuchen-xia/PolyInter. |
| title | One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.16799 |