Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments
arXiv:2010.00716 · doi:10.1109/TRO.2022.3148908
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.
References in corpus (22)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- A Survey of the Recent Architectures of Deep Convolutional Neural Networks
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- FINN: A Framework for Fast, Scalable Binarized Neural Network Inference
- Benchmark Analysis of Representative Deep Neural Network Architectures
- Ternary Weight Networks
- Trained Ternary Quantization
- Particular object retrieval with integral max-pooling of CNN activations
- Training deep neural networks with low precision multiplications
- Learned Step Size Quantization
- VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change
- Back to Simplicity: How to Train Accurate BNNs from Scratch?
- Levelling the Playing Field: A Comprehensive Comparison of Visual Place Recognition Approaches under Changing Conditions
- How Does Batch Normalization Help Binary Training?
- Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks
- Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?
- CAMAL: Context-Aware Multi-layer Attention framework for Lightweight Environment Invariant Visual Place Recognition