paper-with-me

홈 › Papers

ML-LocNet: Improving Object Localization with Multi-view Learning Network

2018-09-01 · ECCV 2018 9 · Xiaopeng Zhang, Yang Yang, Jiashi Feng

This paper addresses Weakly Supervised Object Localization (WSOL) with only image-level supervision. We propose a Multi-view Learning Localization Network (ML-LocNet) by incorporating multi-view learning into a two-phase WSOL model. The multi-view learning would benefit localization due to the complementary relationships among the learned features from different views and the consensus property among the mined instances from each view. In the first phase, the representation is augmented by integrating features learned from multiple views, and in the second phase, the model performs multi-view co-training to enhance localization performance of one view with the help of instances mined from other views, which thus effectively avoids early fitting. ML-LocNet can be easily combined with existing WSOL models to further improve the localization accuracy. Its effectiveness has been proved experimentally. Notably, it achieves 68.6% CorLoc and 49.7% mAP on PASCAL VOC 2007, surpassing the state-of-the-arts by a large margin.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

MULTI-VIEW LEARNINGObject LocalizationWeakly-Supervised Object Localization

Similar Papers 제목 키워드 기반

TransLocNet: Cross-Modal Attention for Aerial-Ground Vehicle Localization with Contrastive Learning

2025-12-11 · Phu Pham, Damon Conover, Aniket Bera arxiv

Aerial-ground localization is difficult due to large viewpoint and modality gaps between ground-level LiDAR and overhead imagery. We propose TransLocNet, a cross-modal attention framework that fuses LiDAR geometry with a…

Contrastive Learning

SegLocNet: Multimodal Localization Network for Autonomous Driving via Bird's-Eye-View Segmentation

2025-02-27 · Zijie Zhou, Zhangshuo Qi, Luqi Cheng, Guangming Xiong

Robust and accurate localization is critical for autonomous driving. Traditional GNSS-based localization methods suffer from signal occlusion and multipath effects in urban environments. Meanwhile, methods relying on hig…

Autonomous DrivingBEV SegmentationPose EstimationSemantic Segmentation

LocNet: Improving Localization Accuracy for Object Detection

2015-11-24 · CVPR 2016 6 · Spyros Gidaris, Nikos Komodakis

We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems. Our model, given a search region, aims at returning the bounding box…

Objectobject-detectionObject DetectionObject Localization

LocNet: Global localization in 3D point clouds for mobile vehicles

2017-12-06 · Huan Yin, Li Tang, Xiaqing Ding, Yue Wang 외

Global localization in 3D point clouds is a challenging problem of estimating the pose of vehicles without any prior knowledge. In this paper, a solution to this problem is presented by achieving place recognition and me…

Pose EstimationRepresentation Learning

PiLocNet: Physics-informed neural network on 3D localization with rotating point spread function

2024-10-17 · Mingda Lu, Zitian Ao, Chao Wang, Sudhakar Prasad 외

For the 3D localization problem using point spread function (PSF) engineering, we propose a novel enhancement of our previously introduced localization neural network, LocNet. The improved network is a physics-informed n…