Excavate Condition-invariant Space by Intrinsic Encoder

Abstract

As the human, we can recognize the places across a wide range of changing environmental conditions such as those caused by weathers, seasons, and day-night cycles. We excavate and memorize the stable semantic structure of different places and scenes. For example, we can recognize tree whether the bare tree in winter or lush tree in summer. Therefore, the intrinsic features that are corresponding to specific semantic contents and condition-invariant of appearance changes can be employed to improve the performance of long-term place recognition significantly. In this paper, we propose a novel intrinsic encoder that excavates the condition-invariant latent space of different places under drastic appearance changes. Our method excavates the space of intrinsic structure and semantic information by proposed self-supervised encoder loss. Different from previous learning based place recognition methods that need paired training data of each place with appearance changes, we employ the weakly-supervised strategy to utilize unpaired set-based training data of different environmental conditions. We conduct comprehensive experiments and show that our semi-supervised intrinsic encoder achieves remarkable performance for place recognition under drastic appearance changes. The proposed intrinsic encoder outperforms the state-of-the-art image-level place recognition methods on standard benchmark Nordland.

arXiv comment10 pages, 5 figures

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Learning Deconvolution Network for Semantic Segmentation
• DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
• Auxiliary Deep Generative Models
• Disentangling factors of variation in deep representations using adversarial training
• On the Performance of ConvNet Features for Place Recognition
• Generative Visual Manipulation on the Natural Image Manifold
• Binary Generative Adversarial Networks for Image Retrieval
• Training a Convolutional Neural Network for Appearance-Invariant Place Recognition
• Deep Learning Features at Scale for Visual Place Recognition