InvKA: Gait Recognition via Invertible Koopman Autoencoder
- URL: http://arxiv.org/abs/2309.14764v2
- Date: Wed, 27 Sep 2023 15:47:58 GMT
- Title: InvKA: Gait Recognition via Invertible Koopman Autoencoder
- Authors: Fan Li, Dong Liang, Jing Lian, Qidong Liu, Hegui Zhu, Jizhao Liu
- Abstract summary: Most gait recognition methods suffer from poor interpretability and high computational cost.
To improve interpretability, we investigate gait features in the embedding space based on Koopman operator theory.
To reduce the computational cost of our algorithm, we use a reversible autoencoder to reduce the model size and eliminate convolutional layers.
- Score: 15.718065380333718
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Most current gait recognition methods suffer from poor interpretability and
high computational cost. To improve interpretability, we investigate gait
features in the embedding space based on Koopman operator theory. The
transition matrix in this space captures complex kinematic features of gait
cycles, namely the Koopman operator. The diagonal elements of the operator
matrix can represent the overall motion trend, providing a physically
meaningful descriptor. To reduce the computational cost of our algorithm, we
use a reversible autoencoder to reduce the model size and eliminate
convolutional layers to compress its depth, resulting in fewer floating-point
operations. Experimental results on multiple datasets show that our method
reduces computational cost to 1% compared to state-of-the-art methods while
achieving competitive recognition accuracy 98% on non-occlusion datasets.
Related papers
- A Mirror Descent-Based Algorithm for Corruption-Tolerant Distributed Gradient Descent [57.64826450787237]
We show how to analyze the behavior of distributed gradient descent algorithms in the presence of adversarial corruptions.
We show how to use ideas from (lazy) mirror descent to design a corruption-tolerant distributed optimization algorithm.
Experiments based on linear regression, support vector classification, and softmax classification on the MNIST dataset corroborate our theoretical findings.
arXiv Detail & Related papers (2024-07-19T08:29:12Z) - QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input [17.017127559393398]
We propose a differentiable soft quantizer, which better simulates the gradient of the round function during backpropagation.
This enables the network to learn from subtle input perturbations.
We further refine the training strategy to ensure convergence while simulating quantization errors.
arXiv Detail & Related papers (2024-05-22T17:34:18Z) - Compression of Structured Data with Autoencoders: Provable Benefit of
Nonlinearities and Depth [83.15263499262824]
We prove that gradient descent converges to a solution that completely disregards the sparse structure of the input.
We show how to improve upon Gaussian performance for the compression of sparse data by adding a denoising function to a shallow architecture.
We validate our findings on image datasets, such as CIFAR-10 and MNIST.
arXiv Detail & Related papers (2024-02-07T16:32:29Z) - NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction.
The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network.
A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
arXiv Detail & Related papers (2022-09-29T04:06:00Z) - Convergent autoencoder approximation of low bending and low distortion
manifold embeddings [5.5711773076846365]
We propose and analyze a novel regularization for learning the encoder component of an autoencoder.
The loss functional is computed via Monte Carlo integration with different sampling strategies for pairs of points on the input manifold.
Our main theorem identifies a loss functional of the embedding map as the $Gamma$-limit of the sampling-dependent loss functionals.
arXiv Detail & Related papers (2022-08-22T10:31:31Z) - A Unified Framework for Implicit Sinkhorn Differentiation [58.56866763433335]
We propose an algorithm that obtains analytical gradients of a Sinkhorn layer via implicit differentiation.
We show that it is computationally more efficient, particularly when resources like GPU memory are scarce.
arXiv Detail & Related papers (2022-05-13T14:45:31Z) - Accelerating Neural Network Inference by Overflow Aware Quantization [16.673051600608535]
Inherited heavy computation of deep neural networks prevents their widespread applications.
We propose an overflow aware quantization method by designing trainable adaptive fixed-point representation.
With the proposed method, we are able to fully utilize the computing power to minimize the quantization loss and obtain optimized inference performance.
arXiv Detail & Related papers (2020-05-27T11:56:22Z) - Differentiable Top-k Operator with Optimal Transport [135.36099648554054]
The SOFT top-k operator approximates the output of the top-k operation as the solution of an Entropic Optimal Transport (EOT) problem.
We apply the proposed operator to the k-nearest neighbors and beam search algorithms, and demonstrate improved performance.
arXiv Detail & Related papers (2020-02-16T04:57:52Z) - Variance Reduction with Sparse Gradients [82.41780420431205]
Variance reduction methods such as SVRG and SpiderBoost use a mixture of large and small batch gradients.
We introduce a new sparsity operator: The random-top-k operator.
Our algorithm consistently outperforms SpiderBoost on various tasks including image classification, natural language processing, and sparse matrix factorization.
arXiv Detail & Related papers (2020-01-27T08:23:58Z)
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.