Attention-based Pyramid Aggregation Network for Visual Place Recognition

Abstract

Visual place recognition is challenging in the urban environment and is usually viewed as a large scale image retrieval task. The intrinsic challenges in place recognition exist that the confusing objects such as cars and trees frequently occur in the complex urban scene, and buildings with repetitive structures may cause over-counting and the burstiness problem degrading the image representations. To address these problems, we present an Attention-based Pyramid Aggregation Network (APANet), which is trained in an end-to-end manner for place recognition. One main component of APANet, the spatial pyramid pooling, can effectively encode the multi-size buildings containing geo-information. The other one, the attention block, is adopted as a region evaluator for suppressing the confusing regional features while highlighting the discriminative ones. When testing, we further propose a simple yet effective PCA power whitening strategy, which significantly improves the widely used PCA whitening by reasonably limiting the impact of over-counting. Experimental evaluations demonstrate that the proposed APANet outperforms the state-of-the-art methods on two place recognition benchmarks, and generalizes well on standard image retrieval datasets.

arXiv commentAccepted to ACM Multimedia 2018

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Squeeze-and-Excitation Networks
• Particular object retrieval with integral max-pooling of CNN activations
• Visual Instance Retrieval with Deep Convolutional Networks

Cited by in corpus (14)

• Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
• MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery
• Adaptive-Attentive Geolocalization from few queries: a hybrid approach
• RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization
• Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines
• Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments
• Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization
• VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning
• Semantic Reinforced Attention Learning for Visual Place Recognition
• Attention-Aware Age-Agnostic Visual Place Recognition
• Learnable Pooling Methods for Video Classification
• Learning Quintuplet Loss for Large-scale Visual Geo-Localization
• Learning to Reconstruct and Segment 3D Objects
• Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations