Effectiveness of Function Matching in Driving Scene Recognition

• URL: http://arxiv.org/abs/2208.09694v1
• Date: Sat, 20 Aug 2022 14:32:20 GMT
• Title: Effectiveness of Function Matching in Driving Scene Recognition
• Authors: Shingo Yashima
• Abstract summary: We experimentally investigate the impact of using such a large amount of unlabeled data for distillation on the performance of student models. We demonstrate that the performance of the compact student model can be improved dramatically and even match the performance of the large-scale teacher.
• Score: 0.571097144710995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge distillation is an effective approach for training compact recognizers required in autonomous driving. Recent studies on image classification have shown that matching student and teacher on a wide range of data points is critical for improving performance in distillation. This concept (called function matching) is suitable for driving scene recognition, where generally an almost infinite amount of unlabeled data are available. In this study, we experimentally investigate the impact of using such a large amount of unlabeled data for distillation on the performance of student models in structured prediction tasks for autonomous driving. Through extensive experiments, we demonstrate that the performance of the compact student model can be improved dramatically and even match the performance of the large-scale teacher by knowledge distillation with massive unlabeled data.

Related papers

• Guiding Attention in End-to-End Driving Models [49.762868784033785]
  Vision-based end-to-end driving models trained by imitation learning can lead to affordable solutions for autonomous driving. We study how to guide the attention of these models to improve their driving quality by adding a loss term during training. In contrast to previous work, our method does not require these salient semantic maps to be available during testing time.
  arXiv  Detail & Related papers  (2024-04-30T23:18:51Z)
• TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation [6.856317526681759]
  Visual place recognition plays a pivotal role in autonomous exploration and navigation of mobile robots. Existing methods overcome this by exploiting powerful yet large networks. We propose a high-performance teacher and lightweight student distillation framework called TSCM.
  arXiv  Detail & Related papers  (2024-04-02T02:29:41Z)
• Understanding the Role of the Projector in Knowledge Distillation [22.698845243751293]
  We revisit the efficacy of knowledge distillation as a function matching and metric learning problem. We verify three important design decisions, namely the normalisation, soft maximum function, and projection layers. We attain a 77.2% top-1 accuracy with DeiT-Ti on ImageNet.
  arXiv  Detail & Related papers  (2023-03-20T13:33:31Z)
• Teaching What You Should Teach: A Data-Based Distillation Method [20.595460553747163]
  We introduce the "Teaching what you Should Teach" strategy into a knowledge distillation framework. We propose a data-based distillation method named "TST" that searches for desirable augmented samples to assist in distilling more efficiently and rationally. To be specific, we design a neural network-based data augmentation module with priori bias, which assists in finding what meets the teacher's strengths but the student's weaknesses.
  arXiv  Detail & Related papers  (2022-12-11T06:22:14Z)
• Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation [65.62538699160085]
  We propose a Directed Acyclic Graph Factorization Machine (KD-DAGFM) to learn the high-order feature interactions from existing complex interaction models for CTR prediction via Knowledge Distillation. KD-DAGFM achieves the best performance with less than 21.5% FLOPs of the state-of-the-art method on both online and offline experiments.
  arXiv  Detail & Related papers  (2022-11-21T03:09:42Z)
• Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation [66.25738680429463]
  Knowledge Distillation (KD) for object detection aims to train a compact detector by transferring knowledge from a teacher model. We propose inconsistent knowledge distillation (IKD) which aims to distill knowledge inherent in the teacher model's counter-intuitive perceptions. Our method outperforms state-of-the-art KD baselines on one-stage, two-stage and anchor-free object detectors.
  arXiv  Detail & Related papers  (2022-09-20T16:36:28Z)
• Adaptive Instance Distillation for Object Detection in Autonomous Driving [3.236217153362305]
  We propose Adaptive Instance Distillation (AID) to selectively impart teacher's knowledge to the student to improve the performance of knowledge distillation. Our AID is also shown to be useful for self-distillation to improve the teacher model's performance.
  arXiv  Detail & Related papers  (2022-01-26T18:06:33Z)
• Knowledge distillation: A good teacher is patient and consistent [71.14922743774864]
  There is a growing discrepancy in computer vision between large-scale models that achieve state-of-the-art performance and models that are affordable in practical applications. We identify certain implicit design choices, which may drastically affect the effectiveness of distillation. We obtain a state-of-the-art ResNet-50 model for ImageNet, which achieves 82.8% top-1 accuracy.
  arXiv  Detail & Related papers  (2021-06-09T17:20:40Z)
• SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data [9.270269467155547]
  SelfHAR is a semi-supervised model that learns to leverage unlabeled datasets to complement small labeled datasets. Our approach combines teacher-student self-training, which distills the knowledge of unlabeled and labeled datasets. SelfHAR is data-efficient, reaching similar performance using up to 10 times less labeled data compared to supervised approaches.
  arXiv  Detail & Related papers  (2021-02-11T15:40:35Z)
• Diverse Complexity Measures for Dataset Curation in Self-driving [80.55417232642124]
  We propose a new data selection method that exploits a diverse set of criteria that quantize interestingness of traffic scenes. Our experiments show that the proposed curation pipeline is able to select datasets that lead to better generalization and higher performance.
  arXiv  Detail & Related papers  (2021-01-16T23:45:02Z)
• Circumventing Outliers of AutoAugment with Knowledge Distillation [102.25991455094832]
  AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks. This paper delves deep into the working mechanism, and reveals that AutoAugment may remove part of discriminative information from the training image. To relieve the inaccuracy of supervision, we make use of knowledge distillation that refers to the output of a teacher model to guide network training.
  arXiv  Detail & Related papers  (2020-03-25T11:51:41Z)

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.