Computer Science > Computer Vision and Pattern Recognition
[Submitted on 17 May 2023 (v1), last revised 12 Apr 2024 (this version, v5)]
Title:HICO-DET-SG and V-COCO-SG: New Data Splits for Evaluating the Systematic Generalization Performance of Human-Object Interaction Detection Models
View PDF HTML (experimental)Abstract:Human-Object Interaction (HOI) detection is a task to localize humans and objects in an image and predict the interactions in human-object pairs. In real-world scenarios, HOI detection models need systematic generalization, i.e., generalization to novel combinations of objects and interactions, because the train data are expected to cover a limited portion of all possible combinations. To evaluate the systematic generalization performance of HOI detection models, we created two new sets of HOI detection data splits named HICO-DET-SG and V-COCO-SG based on the HICO-DET and V-COCO datasets, respectively. When evaluated on the new data splits, HOI detection models with various characteristics performed much more poorly than when evaluated on the original splits. This shows that systematic generalization is a challenging goal in HOI detection. By analyzing the evaluation results, we also gain insights for improving the systematic generalization performance and identify four possible future research directions. We hope that our new data splits and presented analysis will encourage further research on systematic generalization in HOI detection.
Submission history
From: Kentaro Takemoto [view email][v1] Wed, 17 May 2023 05:03:46 UTC (543 KB)
[v2] Wed, 31 May 2023 05:36:42 UTC (1,082 KB)
[v3] Thu, 1 Jun 2023 00:52:04 UTC (1,082 KB)
[v4] Wed, 7 Jun 2023 06:53:07 UTC (1,445 KB)
[v5] Fri, 12 Apr 2024 00:46:26 UTC (2,211 KB)
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.