提出无样本增量交互检测框架，解决动态环境中关系遗忘与零样本新组合识别问题。
Incremental Human-Object Interaction Detection with Invariant Relation Representation Learning
- 解耦物体与关系学习，通过双蒸馏损失提取不变关系特征
- 在HICO-DET和V-COCO上实现更低遗忘率与更强零样本泛化能力
- 适合持续学习场景下的视频理解与人机交互系统开发
在开放世界环境中，人-物交互（HOI）持续演变，挑战传统封闭世界下的HOI检测模型。受人类渐进式知识获取启发，本文探索增量式人-物交互检测（IHOID），旨在使智能体具备在动态环境中识别人-物关系的能力。该设定不仅面临增量学习中的灾难性遗忘问题，还存在交互漂移及对顺序到达数据中零样本交互组合的检测难题。为此，本文提出一种新颖的无样本增量关系蒸馏（IRD）框架。IRD将物体与关系的学习解耦，并引入两种独特的蒸馏损失，以学习共享相同关系的不同交互组合间的不变关系特征。在HICO-DET和V-COCO数据集上的大量实验表明，该方法在缓解遗忘、增强对交互漂移的鲁棒性以及零样本HOI泛化方面优于当前最优基线。代码已开源。
原文摘要 · Abstract (English)
In open-world environments, human-object interactions (HOIs) evolve continuously, challenging conventional closed-world HOI detection models. Inspired by humans' ability to progressively acquire knowledge, we explore incremental HOI detection (IHOID) to develop agents capable of discerning human-object relations in such dynamic environments. This setup confronts not only the common issue of catastrophic forgetting in incremental learning but also distinct challenges posed by interaction drift and detecting zero-shot HOI combinations with sequentially arriving data. Therefore, we propose a novel exemplar-free incremental relation distillation (IRD) framework. IRD decouples the learning of objects and relations, and introduces two unique distillation losses for learning invariant relation features across different HOI combinations that share the same relation. Extensive experiments on HICO-DET and V-COCO datasets demonstrate the superiority of our method over state-of-the-art baselines in mitigating forgetting, strengthening robustness against interaction drift, and generalization on zero-shot HOIs. Code is available at \href{https://github.com/weiyana/ContinualHOI}{this HTTP URL}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。