RoHOI: Robustness Benchmark for Human-Object Interaction Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911205356994560 |
|---|---|
| author | Wen, Di Peng, Kunyu Yang, Kailun Chen, Yufan Liu, Ruiping Zheng, Junwei Roitberg, Alina Paudel, Danda Pani Van Gool, Luc Stiefelhagen, Rainer |
| author_facet | Wen, Di Peng, Kunyu Yang, Kailun Chen, Yufan Liu, Ruiping Zheng, Junwei Roitberg, Alina Paudel, Danda Pani Van Gool, Luc Stiefelhagen, Rainer |
| contents | Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support. However, models trained on clean datasets degrade in real-world conditions due to unforeseen corruptions, leading to inaccurate predictions. To address this, we introduce the first robustness benchmark for HOI detection, evaluating model resilience under diverse challenges. Despite advances, current models struggle with environmental variability, occlusions, and noise. Our benchmark, RoHOI, includes 20 corruption types based on the HICO-DET and V-COCO datasets and a new robustness-focused metric. We systematically analyze existing models in the HOI field, revealing significant performance drops under corruptions. To improve robustness, we propose a Semantic-Aware Masking-based Progressive Learning (SAMPL) strategy to guide the model to be optimized based on holistic and partial cues, thus dynamically adjusting the model's optimization to enhance robust feature learning. Extensive experiments show that our approach outperforms state-of-the-art methods, setting a new standard for robust HOI detection. Benchmarks, datasets, and code are available at https://github.com/KratosWen/RoHOI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RoHOI: Robustness Benchmark for Human-Object Interaction Detection Wen, Di Peng, Kunyu Yang, Kailun Chen, Yufan Liu, Ruiping Zheng, Junwei Roitberg, Alina Paudel, Danda Pani Van Gool, Luc Stiefelhagen, Rainer Computer Vision and Pattern Recognition Human-Computer Interaction Robotics Image and Video Processing Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support. However, models trained on clean datasets degrade in real-world conditions due to unforeseen corruptions, leading to inaccurate predictions. To address this, we introduce the first robustness benchmark for HOI detection, evaluating model resilience under diverse challenges. Despite advances, current models struggle with environmental variability, occlusions, and noise. Our benchmark, RoHOI, includes 20 corruption types based on the HICO-DET and V-COCO datasets and a new robustness-focused metric. We systematically analyze existing models in the HOI field, revealing significant performance drops under corruptions. To improve robustness, we propose a Semantic-Aware Masking-based Progressive Learning (SAMPL) strategy to guide the model to be optimized based on holistic and partial cues, thus dynamically adjusting the model's optimization to enhance robust feature learning. Extensive experiments show that our approach outperforms state-of-the-art methods, setting a new standard for robust HOI detection. Benchmarks, datasets, and code are available at https://github.com/KratosWen/RoHOI. |
| title | RoHOI: Robustness Benchmark for Human-Object Interaction Detection |
| topic | Computer Vision and Pattern Recognition Human-Computer Interaction Robotics Image and Video Processing |
| url | https://arxiv.org/abs/2507.09111 |