Learning Transferable Reward for Query Object Localization with Policy Adaptation
Tingfeng Li, Shaobo Han, Martin Renqiang Min, Dimitris N. Metaxas
Abstract
We propose a reinforcement learning based approach to query object localization, for which an agent is trained to localize objects of interest specified by a small exemplary set. We learn a transferable reward signal formulated using the exemplary set by ordinal metric learning. Our proposed method enables test-time policy adaptation to new environments where the reward signals are not readily available, and outperforms fine-tuning approaches that are limited to annotated images. In addition, the transferable reward allows repurposing the trained agent from one specific class to another class. Experiments on corrupted MNIST, CU-Birds, and COCO datasets demonstrate the effectiveness of our approach 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on8
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
- Habitat: A Platform for Embodied AI ResearchManolis Savva, Jitendra Malik, Devi Parikh, Dhruv Batra et al.ICCV 2019 · 1,863 citations
- Test-Time Training with Self-Supervision for Generalization under Distribution ShiftsYu Sun, Xiaolong Wang, Zhuang Liu, John Miller et al.ICML 2020 · 1,220 citations
- Few-Shot Object Detection via Feature ReweightingBingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu et al.ICCV 2019 · 835 citations
Related papers
- Reinforced Attention for Few-Shot Learning and BeyondJie Hong, Pengfei Fang, Weihao Li, Tong Zhang et al.CVPR 2021
- FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy OptimizationMohammed Asad Karim, Vinay Kumar VermaICML 2026 · 1 citation
- Efficient Meta Reinforcement Learning for Preference-based Fast AdaptationZhizhou Ren, Anji Liu, Yitao Liang, Jian Peng et al.NeurIPS 2022 · 11 citations
- QORA: Zero-Shot Transfer via Interpretable Object-Relational Model LearningGabriel Stella, Dmitri LoguinovICML 2024 · 1 citation
- Offline RL by Reward-Weighted Fine-Tuning for Conversation OptimizationSubhojyoti Mukherjee, Viet Dac Lai, Raghavendra Addanki, Ryan Rossi et al.NeurIPS 2025 · 12 citations
