Memory-based Error Label Suppression for Embodied Self-Improving Object Detection
文献类型：会议论文
| 作者 | Deng JR(邓杰仁)1,2 ; Zhang HJ(张好剑)2; Hu JH(胡建华)2; Wang YK(王云宽)2
|
| 出版日期 | 2024-06-04 |
| 会议日期 | 2024-8-28 |
| 会议地点 | 意大利巴里 |
| 英文摘要 | This paper introduces a novel method for embodied self-improving object detection, aimed at enhancing the object detection model by gathering additional labeled samples post-pre-training without the need for human supervision. Current self-improving strategies autonomously label new samples using 3D consistency, yet they often incorporate a substantial amount of mislabeled samples, thereby diminishing the potential performance improvement to the model. To counter this issue, we propose a memory-based method for suppressing error labels to minimize their adverse impact. This error label suppression mechanism includes LoRA output constraint and exemplar prototype constraints, which leverage explicit memories of correct prototypes and implicit memories of correctly learned parameters, respectively. These mechanisms effectively reduce the negative effects of erroneous labels on the model’s learning process. Building upon the robustness provided by our Memory-Based Error Label Suppression, we further incorporates Cross-View Redundant Labeling to introduce a higher quantity of accurate samples, thus amplifying the benefits of embodied self-improving. Experimental results demonstrate that our method exhibits more robustness against erroneous samples compared to existing methods, leading to significantly performance improvement. |
| 会议录出版者 | IEEE |
| 语种 | 英语 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57431]  |
| 专题 | 智能制造技术与系统研究中心_先进制造与自动化 |
| 通讯作者 | Hu JH(胡建华) |
| 作者单位 | 1.中国科学院大学 2.中国科学院自动化研究所 |
| 推荐引用方式 GB/T 7714 | Deng JR,Zhang HJ,Hu JH,et al. Memory-based Error Label Suppression for Embodied Self-Improving Object Detection[C]. 见:. 意大利巴里. 2024-8-28. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。