PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation

• URL: http://arxiv.org/abs/2108.10710v1
• Date: Tue, 24 Aug 2021 13:19:08 GMT
• Title: PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation
• Abstract summary: We utilize neural architecture search to develop a new family of face recognition models, namely PocketNet. We present an experimental evaluation and comparisons with the recent compact face recognition models on nine different benchmarks. PocketNets have consistently advanced the state-of-the-art (SOTA) face recognition performance on nine mainstream benchmarks.
• Score: 5.858033242850427
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have rapidly become the mainstream method for face recognition. However, deploying such models that contain an extremely large number of parameters to embedded devices or in application scenarios with limited memory footprint is challenging. In this work, we present an extremely lightweight and accurate face recognition solution. We utilize neural architecture search to develop a new family of face recognition models, namely PocketNet. We also propose to enhance the verification performance of the compact model by presenting a novel training paradigm based on knowledge distillation, namely the multi-step knowledge distillation. We present an extensive experimental evaluation and comparisons with the recent compact face recognition models on nine different benchmarks including large-scale evaluation benchmarks such as IJB-B, IJB-C, and MegaFace. PocketNets have consistently advanced the state-of-the-art (SOTA) face recognition performance on nine mainstream benchmarks when considering the same level of model compactness. With 0.92M parameters, our smallest network PocketNetS-128 achieved very competitive results to recent SOTA compacted models that contain more than 4M parameters. Training codes and pre-trained models are publicly released https://github.com/fdbtrs/PocketNet.

Related papers

• PocketSR: The Super-Resolution Expert in Your Pocket Mobiles [69.26751136689533]
  Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones.<n>Existing methods leveraging large generative models demonstrate impressive results, but the high computational cost and latency make them impractical for edge deployment.<n>We introduce PocketSR, an ultra-lightweight, single-step model that brings generative modeling capabilities to RealSR while maintaining high fidelity.
  arXiv  Detail & Related papers  (2025-10-03T13:56:18Z)
• Computer Vision Model Compression Techniques for Embedded Systems: A Survey [75.38606213726906]
  This paper covers the main model compression techniques applied for computer vision tasks. We present the characteristics of compression subareas, compare different approaches, and discuss how to choose the best technique. We also share codes to assist researchers and new practitioners in overcoming initial implementation challenges.
  arXiv  Detail & Related papers  (2024-08-15T16:41:55Z)
• GhostNetV3: Exploring the Training Strategies for Compact Models [41.63605520952545]
  We introduce a strong training strategy for compact models. We find that the appropriate designs of re- parameterization and knowledge distillation are crucial for training high-performance compact models. equipped with our strategy, GhostNetV3 1.3$times$ achieves a top-1 accuracy of 79.1% with only 269M FLOPs and a latency of 14.46ms on mobile devices.
  arXiv  Detail & Related papers  (2024-04-17T09:33:31Z)
• SqueezerFaceNet: Reducing a Small Face Recognition CNN Even More Via Filter Pruning [55.84746218227712]
  We develop SqueezerFaceNet, a light face recognition network which less than 1M parameters. We show that it can be further reduced (up to 40%) without an appreciable loss in performance.
  arXiv  Detail & Related papers  (2023-07-20T08:38:50Z)
• A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification [1.9019295680940274]
  We present a robust and low complexity deep learning model for Remote Sensing Image Classification (RSIC) By conducting extensive experiments on the benchmark datasets NWPU-RESISC45, we achieve a robust and low-complexity model.
  arXiv  Detail & Related papers  (2022-11-05T06:14:30Z)
• Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors [68.8204255655161]
  This paper compares four state-of-the-art algorithms in two real applications: gesture recognition based on accelerometer data and image classification. Our results confirm these systems' reliability and the feasibility of deploying them in tiny-memory MCUs.
  arXiv  Detail & Related papers  (2022-09-01T17:05:20Z)
• LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network [2.624902795082451]
  LIDSNet is a novel lightweight on-device intent detection model. We show that our model is at least 41x lighter and 30x faster during inference than MobileBERT on Samsung Galaxy S20 device.
  arXiv  Detail & Related papers  (2021-10-06T18:20:37Z)
• When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model [87.25037167380522]
  We propose a model that is accurate, robust, efficient, generalizable, and end-to-end trainable. In order to achieve a better accuracy, we propose two lightweight modules. DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one.
  arXiv  Detail & Related papers  (2021-05-27T13:51:42Z)
• Real-time Denoising and Dereverberation with Tiny Recurrent U-Net [12.533488149023025]
  We propose Tiny Recurrent U-Net (TRU-Net), a lightweight online inference model that matches the performance of current state-of-the-art models. The size of the quantized version of TRU-Net is 362 kilobytes, which is small enough to be deployed on edge devices. Results of both objective and subjective evaluations have shown that our model can achieve competitive performance with the current state-of-the-art models.
  arXiv  Detail & Related papers  (2021-02-05T14:46:41Z)
• The FaceChannel: A Fast & Furious Deep Neural Network for Facial Expression Recognition [71.24825724518847]
  Current state-of-the-art models for automatic Facial Expression Recognition (FER) are based on very deep neural networks that are effective but rather expensive to train. We formalize the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks. We demonstrate how our model achieves a comparable, if not better, performance to the current state-of-the-art in FER.
  arXiv  Detail & Related papers  (2020-09-15T09:25:37Z)
• The FaceChannel: A Light-weight Deep Neural Network for Facial Expression Recognition [71.24825724518847]
  Current state-of-the-art models for automatic FER are based on very deep neural networks that are difficult to train. We formalize the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks. We demonstrate how the FaceChannel achieves a comparable, if not better, performance, as compared to the current state-of-the-art in FER.
  arXiv  Detail & Related papers  (2020-04-17T12:03:14Z)

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.