mlsanityData to 14 Oct 2026

Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition

arXiv 2306.09822 ↗First posted 16 Jun 2023cs.CV cs.NA math.NAcited by 0

Not on the map. Why?

Abstract (arXiv)

Pedestrian Attribute Recognition (PAR) focuses on identifying various attributes in pedestrian images, with key applications in person retrieval, suspect re-identification, and soft biometrics. However, Deep Neural Networks (DNNs) for PAR often suffer from over-parameterization and high computational complexity, making them unsuitable for resource-constrained devices. Traditional tensor-based compression methods typically factorize layers without adequately preserving the gradient direction during compression, leading to inefficient compression and a significant accuracy loss. In this work, we propose a novel approach for determining the optimal ranks of low-rank layers, ensuring that the gradient direction of the compressed model closely aligns with that of the original model. This means that the compressed model effectively preserves the update direction of the full model, enabling more efficient compression for PAR tasks. The proposed procedure optimizes the compression ranks for each layer within the ALM model, followed by compression using CPD-EPC or truncated SVD. This results in a reduction in model complexity while maintaining high performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 39 references that are in the map. First posted on arXiv 16 Jun 2023.

Builds on

16 of 39 references.

References · 16

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  3. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 284
  4. 2015Tensorizing Neural Networkscited by 250
  5. 2013Predicting Parameters in Deep Learningcited by 224
  6. 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 203
  7. 2014Compressing Deep Convolutional Networks using Vector Quantizationcited by 195
  8. 2018The Singular Values of Convolutional Layerscited by 95
  9. 2013Fast Training of Convolutional Networks through FFTscited by 89
  10. 2017HydraPlus-Net: Attentive Deep Features for Pedestrian Analysiscited by 89
  11. 2020Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Networkcited by 74
  12. 2020Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsificationcited by 53
4 more
  1. 2021Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Frameworkcited by 52
  2. 2019Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localizationcited by 46
  3. 2017CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compressioncited by 30
  4. 2023Tensor Decomposition for Model Reduction in Neural Networks: A Reviewcited by 14

Built on by

Not cited yet.