Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments

• URL: http://arxiv.org/abs/2010.00716v2
• Date: Sun, 23 Jan 2022 10:48:16 GMT
• Title: Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments
• Authors: Bruno Ferrarini, Michael Milford, Klaus D. McDonald-Maier and Shoaib Ehsan
• Abstract summary: Visual place recognition (VPR) is a robot's ability to determine whether a place was visited before using visual data. CNN-based approaches are unsuitable for resource-constrained platforms, such as small robots and drones. We propose a new class of highly compact models that drastically reduces the memory requirements and computational effort.
• Score: 24.674034243725455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual place recognition (VPR) is a robot's ability to determine whether a place was visited before using visual data. While conventional hand-crafted methods for VPR fail under extreme environmental appearance changes, those based on convolutional neural networks (CNNs) achieve state-of-the-art performance but result in heavy runtime processes and model sizes that demand a large amount of memory. Hence, CNN-based approaches are unsuitable for resource-constrained platforms, such as small robots and drones. In this paper, we take a multi-step approach of decreasing the precision of model parameters, combining it with network depth reduction and fewer neurons in the classifier stage to propose a new class of highly compact models that drastically reduces the memory requirements and computational effort while maintaining state-of-the-art VPR performance. To the best of our knowledge, this is the first attempt to propose binary neural networks for solving the visual place recognition problem effectively under changing conditions and with significantly reduced resource requirements. Our best-performing binary neural network, dubbed FloppyNet, achieves comparable VPR performance when considered against its full-precision and deeper counterparts while consuming 99% less memory and increasing the inference speed seven times.

Related papers

• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• OLLA: Decreasing the Memory Usage of Neural Networks by Optimizing the Lifetime and Location of Arrays [6.418232942455968]
  OLLA is an algorithm that optimize the lifetime and memory location of the tensors used to train neural networks. We present several techniques to simplify the encoding of the problem, and enable our approach to scale to the size of state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2022-10-24T02:39:13Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Highly-Efficient Binary Neural Networks for Visual Place Recognition [24.674034243725455]
  VPR is a fundamental task for autonomous navigation as it enables a robot to localize itself in the workspace when a known location is detected. CNN-based techniques archive state-of-the-art VPR performance but are computationally intensive and energy demanding. This paper presents a class of BNNs for VPR that combines depthwise separable factorization and binarization to replace the first convolutional layer.
  arXiv  Detail & Related papers  (2022-02-24T22:05:11Z)
• Event Neural Networks [13.207573300016277]
  Event Neural Networks (EvNets) leverage repetition to achieve considerable savings for video inference tasks. We show that it is possible to transform virtually any conventional neural into an EvNet. We demonstrate the effectiveness of our method on several state-of-the-art neural networks for both high- and low-level visual processing.
  arXiv  Detail & Related papers  (2021-12-02T00:08:48Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Binary Graph Neural Networks [69.51765073772226]
  Graph Neural Networks (GNNs) have emerged as a powerful and flexible framework for representation learning on irregular data. In this paper, we present and evaluate different strategies for the binarization of graph neural networks. We show that through careful design of the models, and control of the training process, binary graph neural networks can be trained at only a moderate cost in accuracy on challenging benchmarks.
  arXiv  Detail & Related papers  (2020-12-31T18:48:58Z)
• EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer [82.28607779710066]
  We explore the application of neuroevolution, a form of neural architecture search inspired by biological evolution, in the design of 2D human pose networks. Our method produces network designs that are more efficient and more accurate than state-of-the-art hand-designed networks.
  arXiv  Detail & Related papers  (2020-11-17T05:56:16Z)
• Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks [0.0]
  We propose and compare two neural networks based on the convolutional long short-term memory unit, namely ConvLSTM. We show that the proposed models achieve competitive recognition accuracies with lower computational cost compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-06-13T23:35:59Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.