paper-with-me

홈 › Papers

Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection

2022-02-19 · Xinpeng Liu, Yong-Lu Li, Cewu Lu

Human-Object Interaction (HOI) detection plays a core role in activity understanding. As a compositional learning problem (human-verb-object), studying its generalization matters. However, widely-used metric mean average precision (mAP) fails to model the compositional generalization well. Thus, we propose a novel metric, mPD (mean Performance Degradation), as a complementary of mAP to evaluate the performance gap among compositions of different objects and the same verb. Surprisingly, mPD reveals that previous methods usually generalize poorly. With mPD as a cue, we propose Object Category (OC) Immunity to boost HOI generalization. The idea is to prevent model from learning spurious object-verb correlations as a short-cut to over-fit the train set. To achieve OC-immunity, we propose an OC-immune network that decouples the inputs from OC, extracts OC-immune representations, and leverages uncertainty quantification to generalize to unseen objects. In both conventional and zero-shot experiments, our method achieves decent improvements. To fully evaluate the generalization, we design a new and more difficult benchmark, on which we present significant advantage. The code is available at https://github.com/Foruck/OC-Immunity.

📄 PDF Abstract BibTeX arXiv:2202.09492

Code (1)

foruck/oc-immunity 공식 구현 pytorch

Tasks

Human-Object Interaction DetectionObjectUncertainty Quantification

Similar Papers 제목 키워드 기반

DVF: Advancing Robust and Accurate Fine-Grained Image Retrieval with Retrieval Guidelines

2024-04-24 · Xin Jiang, Hao Tang, Rui Yan, Jinhui Tang 외

Fine-grained image retrieval (FGIR) is to learn visual representations that distinguish visually similar objects while maintaining generalization. Existing methods propose to generate discriminative features, but rarely …

Image RetrievalRetrieval

A new oscillatory regime in two-strain epidemic models with partial cross-immunity

2024-12-10 · Nir Gavish

Infectious diseases often involve multiple strains that interact through the immune response generated after an infection. This study investigates the conditions under which a two-strain epidemic model with partial cross…

Object-Category Aware Reinforcement Learning

2022-10-13 · Qi Yi, Rui Zhang, Shaohui Peng, Jiaming Guo 외

Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL. Recent works that try to solve OORL tasks without additional feature engineer…

Feature EngineeringObjectObject Discoveryreinforcement-learning+2

Bifurcations and multi-stability in a model of cytokine-mediated autoimmunity

2018-10-28

This paper investigates the dynamics of immune response and autoimmunity with particular emphasis on the role of regulatory T cells (Tregs), T cells with different activation thresholds, and cytokines in mediating T cell…

Self-organizing maps and generalization: an algorithmic description of Numerosity and Variability Effects

2018-02-26 · Valentina Gliozzi, Kim Plunkett

Category, or property generalization is a central function in the human cognition. It plays a crucial role in a variety of domains, such as learning, everyday reasoning, specialized reasoning, and decision making. Judgin…

Decision Making