Compression of descriptor models for mobile applications
- URL: http://arxiv.org/abs/2001.03102v3
- Date: Fri, 5 Feb 2021 10:41:09 GMT
- Title: Compression of descriptor models for mobile applications
- Authors: Roy Miles, Krystian Mikolajczyk
- Abstract summary: We evaluate the computational cost, model size, and matching accuracy tradeoffs for deep neural networks.
We observe a significant redundancy in the learned weights, which we exploit through the use of depthwise separable layers.
We propose the Convolution-Depthwise-Pointwise(CDP) layer, which provides a means of interpolating between the standard and depthwise separable convolutions.
- Score: 26.498907514590165
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep neural networks have demonstrated state-of-the-art performance for
feature-based image matching through the advent of new large and diverse
datasets. However, there has been little work on evaluating the computational
cost, model size, and matching accuracy tradeoffs for these models. This paper
explicitly addresses these practical metrics by considering the
state-of-the-art HardNet model. We observe a significant redundancy in the
learned weights, which we exploit through the use of depthwise separable layers
and an efficient Tucker decomposition. We demonstrate that a combination of
these methods is very effective, but still sacrifices the top-end accuracy. To
resolve this, we propose the Convolution-Depthwise-Pointwise(CDP) layer, which
provides a means of interpolating between the standard and depthwise separable
convolutions. With this proposed layer, we can achieve an 8 times reduction in
the number of parameters on the HardNet model, 13 times reduction in the
computational complexity, while sacrificing less than 1% on the overall
accuracy across theHPatchesbenchmarks. To further demonstrate the
generalisation of this approach, we apply it to the state-of-the-art SuperPoint
model, where we can significantly reduce the number of parameters and
floating-point operations, with minimal degradation in the matching accuracy.
Related papers
- WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration [68.25711405944239]
Deep image registration has demonstrated exceptional accuracy and fast inference.
Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner.
We introduce a model-driven WiNet that incrementally estimates scale-wise wavelet coefficients for the displacement/velocity field across various scales.
arXiv Detail & Related papers (2024-07-18T11:51:01Z) - Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision
Post-Training Quantization [7.392278887917975]
We propose a mixed-precision post training quantization approach that assigns different numerical precisions to tensors in a network based on their specific needs.
Our experiments demonstrate latency reductions compared to a 16-bit baseline of $25.48%$, $21.69%$, and $33.28%$ respectively.
arXiv Detail & Related papers (2023-06-08T02:18:58Z) - Pushing the Limits of Asynchronous Graph-based Object Detection with
Event Cameras [62.70541164894224]
We introduce several architecture choices which allow us to scale the depth and complexity of such models while maintaining low computation.
Our method runs 3.7 times faster than a dense graph neural network, taking only 8.4 ms per forward pass.
arXiv Detail & Related papers (2022-11-22T15:14:20Z) - Deep learning model compression using network sensitivity and gradients [3.52359746858894]
We present model compression algorithms for both non-retraining and retraining conditions.
In the first case, we propose the Bin & Quant algorithm for compression of the deep learning models using the sensitivity of the network parameters.
In the second case, we propose our novel gradient-weighted k-means clustering algorithm (GWK)
arXiv Detail & Related papers (2022-10-11T03:02:40Z) - Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks [20.374784902476318]
Pruning, as a method to introduce zeros to model weights, has shown to be an effective method to provide good trade-offs between model accuracy and computation efficiency.
Some modern processors are equipped with fast on-chip scratchpad memories and gather/scatter engines that perform indirect load and store operations on such memories.
In this work, we propose a set of novel sparse patterns, named gather-scatter (GS) patterns, to utilize the scratchpad memories and gather/scatter engines to speed up neural network inferences.
arXiv Detail & Related papers (2021-12-20T22:55:45Z) - Manifold Regularized Dynamic Network Pruning [102.24146031250034]
This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks.
The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
arXiv Detail & Related papers (2021-03-10T03:59:03Z) - AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation.
Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
arXiv Detail & Related papers (2020-07-14T09:07:29Z) - Training with Quantization Noise for Extreme Model Compression [57.51832088938618]
We tackle the problem of producing compact models, maximizing their accuracy for a given model size.
A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator.
In this paper, we extend this approach to work beyond int8 fixed-point quantization with extreme compression methods.
arXiv Detail & Related papers (2020-04-15T20:10:53Z) - Highly Efficient Salient Object Detection with 100K Parameters [137.74898755102387]
We propose a flexible convolutional module, namely generalized OctConv (gOctConv), to efficiently utilize both in-stage and cross-stages multi-scale features.
We build an extremely light-weighted model, namely CSNet, which achieves comparable performance with about 0.2% (100k) of large models on popular object detection benchmarks.
arXiv Detail & Related papers (2020-03-12T07:00:46Z)
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.