Distilling Facial Knowledge With Teacher-Tasks: Semantic-Segmentation-Features For Pose-Invariant Face-Recognition

• URL: http://arxiv.org/abs/2209.01115v1
• Date: Fri, 2 Sep 2022 15:24:22 GMT
• Title: Distilling Facial Knowledge With Teacher-Tasks: Semantic-Segmentation-Features For Pose-Invariant Face-Recognition
• Authors: Ali Hassani, Zaid El Shair, Rafi Ud Duala Refat, Hafiz Malik
• Abstract summary: The proposed Seg-Distilled-ID network jointly learns identification and semantic-segmentation tasks, where the segmentation task is then "distilled" Performance is benchmarked against three state-of-the-art encoders on a publicly available data-set. Experimental evaluations show the Seg-Distilled-ID network shows notable benefits, achieving 99.9% test-accuracy in comparison to 81.6% on ResNet-101, 96.1% on VGG-19 and 96.3% on InceptionV3.
• Score: 1.1811442086145123
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This paper demonstrates a novel approach to improve face-recognition pose-invariance using semantic-segmentation features. The proposed Seg-Distilled-ID network jointly learns identification and semantic-segmentation tasks, where the segmentation task is then "distilled" (MobileNet encoder). Performance is benchmarked against three state-of-the-art encoders on a publicly available data-set emphasizing head-pose variations. Experimental evaluations show the Seg-Distilled-ID network shows notable robustness benefits, achieving 99.9% test-accuracy in comparison to 81.6% on ResNet-101, 96.1% on VGG-19 and 96.3% on InceptionV3. This is achieved using approximately one-tenth of the top encoder's inference parameters. These results demonstrate distilling semantic-segmentation features can efficiently address face-recognition pose-invariance.

Related papers

• SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation [27.367986520072147]
  Unsupervised semantic segmentation is a challenging task that segments images into semantic groups without manual annotation. We propose a novel approach called SmooSeg that harnesses self-supervised learning methods to model the closeness relationships among observations as smoothness signals. Our SmooSeg significantly outperforms STEGO in terms of pixel accuracy on three datasets.
  arXiv  Detail & Related papers  (2023-10-27T03:29:25Z)
• Free-text Keystroke Authentication using Transformers: A Comparative Study of Architectures and Loss Functions [1.0152838128195467]
  Keystroke biometrics is a promising approach for user identification and verification, leveraging the unique patterns in individuals' typing behavior. We propose a Transformer-based network that employs self-attention to extract informative features from keystroke sequences. Our model surpasses the previous state-of-the-art in free-text keystroke authentication.
  arXiv  Detail & Related papers  (2023-10-18T00:34:26Z)
• PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition [29.05343410791649]
  We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We show that a part-centric learning step aggregates and contrasts representations of parts within an image. This improves the performance on image classification and part segmentation tasks across datasets.
  arXiv  Detail & Related papers  (2023-09-25T02:08:48Z)
• Learning Diversified Feature Representations for Facial Expression Recognition in the Wild [97.14064057840089]
  We propose a mechanism to diversify the features extracted by CNN layers of state-of-the-art facial expression recognition architectures. Experimental results on three well-known facial expression recognition in-the-wild datasets, AffectNet, FER+, and RAF-DB, show the effectiveness of our method.
  arXiv  Detail & Related papers  (2022-10-17T19:25:28Z)
• Segmentation of Weakly Visible Environmental Microorganism Images Using Pair-wise Deep Learning Features [7.837413642215894]
  A Pairwise Deep Learning Feature Network (PDLF-Net) is proposed in this study. The use of PDLFs enables the network to focus more on the foreground (EMs) by concatenating the pairwise deep learning features of each image to different blocks of the base model SegNet. PDLF-Net achieves outstanding segmentation results of 89.24%, 63.20%, 77.27%, 35.15%, 89.72%, 91.44% and 89.30% on the accuracy, IoU, Dice, VOE, sensitivity, precision and specificity, respectively.
  arXiv  Detail & Related papers  (2022-08-31T16:37:52Z)
• TransFA: Transformer-based Representation for Face Attribute Evaluation [87.09529826340304]
  We propose a novel textbftransformer-based representation for textbfattribute evaluation method (textbfTransFA) The proposed TransFA achieves superior performances compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-07-12T10:58:06Z)
• Distilling Inter-Class Distance for Semantic Segmentation [17.76592932725305]
  We propose an Inter-class Distance Distillation (IDD) method to transfer the inter-class distance in the feature space from the teacher network to the student network. Our method is helpful to improve the accuracy of semantic segmentation models and achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-05-07T13:13:55Z)
• Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learning [96.72850130126294]
  We propose an Iris U-transformer (IrisUsformer) for accurate and reliable iris segmentation. For better accuracy, we elaborately design IrisUsformer by adopting position-sensitive operation and re-packaging transformer block. We show that IrisUsformer achieves better segmentation accuracy using 35% MACs of the SOTA IrisParseNet.
  arXiv  Detail & Related papers  (2021-10-20T01:37:19Z)
• Unsupervised Pretraining for Object Detection by Patch Reidentification [72.75287435882798]
  Unsupervised representation learning achieves promising performances in pre-training representations for object detectors. This work proposes a simple yet effective representation learning method for object detection, named patch re-identification (Re-ID) Our method significantly outperforms its counterparts on COCO in all settings, such as different training iterations and data percentages.
  arXiv  Detail & Related papers  (2021-03-08T15:13:59Z)
• Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation [90.87105131054419]
  We present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. We validate the proposed model on the Cityscapes dataset, where all three modules demonstrate significant performance gains.
  arXiv  Detail & Related papers  (2020-12-19T21:18:03Z)
• Dense Contrastive Learning for Self-Supervised Visual Pre-Training [102.15325936477362]
  We present dense contrastive learning, which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only 1% slower)
  arXiv  Detail & Related papers  (2020-11-18T08:42:32Z)

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.