paper-with-me

Papers

DecAug: Augmenting HOI Detection via Decomposition

2020-10-02 · Yichen Xie, Hao-Shu Fang, Dian Shao, Yong-Lu Li, Cewu Lu

Human-object interaction (HOI) detection requires a large amount of annotated data. Current algorithms suffer from insufficient training samples and category imbalance within datasets. To increase data efficiency, in this paper, we propose an efficient and effective data augmentation method called DecAug for HOI detection. Based on our proposed object state similarity metric, object patterns across different HOIs are shared to augment local object appearance features without changing their state. Further, we shift spatial correlation between humans and objects to other feasible configurations with the aid of a pose-guided Gaussian Mixture Model while preserving their interactions. Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset for two advanced models. Specifically, interactions with fewer samples enjoy more notable improvement. Our method can be easily integrated into various HOI detection models with negligible extra computational consumption. Our code will be made publicly available.

📄 PDF Abstract BibTeX arXiv:2010.01007

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDomain GeneralizationHuman-Object Interaction DetectionObject

Similar Papers 제목 키워드 기반

DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation

2020-12-17 · Haoyue Bai, Rui Sun, Lanqing Hong, Fengwei Zhou 외

While deep learning demonstrates its strong ability to handle independent and identically distributed (IID) data, it often suffers from out-of-distribution (OoD) generalization, where the test data come from another dist…

Domain GeneralizationImage ClassificationOut-of-Distribution Generalization

PointAugmenting: Cross-Modal Augmentation for 3D Object Detection

2021-06-19 · CVPR 2021 1 · Chunwei Wang, Chao Ma, Ming Zhu, Xiaokang Yang

Camera and LiDAR are two complementary sensors for 3D object detection in the autonomous driving context. Camera provides rich texture and color cues while LiDAR specializes in relative distance sensing. The challeng…

3D Object DetectionAutonomous DrivingData AugmentationObject+3

Algorithmic progress in computer vision

2022-12-10 · Ege Erdil, Tamay Besiroglu

We investigate algorithmic progress in image classification on ImageNet, perhaps the most well-known test bed for computer vision. We estimate a model, informed by work on neural scaling laws, and infer a decomposition o…

Attributeimage-classificationImage Classification

AGILE: Approach-based Grasp Inference Learned from Element Decomposition

2024-02-02 · MohammadHossein Koosheshi, Hamed Hosseini, Mehdi Tale Masouleh, Ahmad Kalhor 외

Humans, this species expert in grasp detection, can grasp objects by taking into account hand-object positioning information. This work proposes a method to enable a robot manipulator to learn the same, grasping objects …

Domain AdaptationRobotic Grasping

End-to-End Neural Context Reconstruction in Chinese Dialogue

2019-08-01 · WS 2019 8 · Wei Yang, Rui Qiao, Haocheng Qin, Amy Sun 외

We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in i…

coreference-resolutionCoreference ResolutionPOSPosition+1