Multi-scale Feature Extraction and Fusion for Online Knowledge Distillation

نویسندگان

چکیده

Online knowledge distillation conducts transfer among all student models to alleviate the reliance on pre-trained models. However, existing online methods rely heavily prediction distributions and neglect further exploration of representational knowledge. In this paper, we propose a novel Multi-scale Feature Extraction Fusion method (MFEF) for distillation, which comprises three key components: Extraction, Dual-attention Fusion, towards generating more informative feature maps distillation. The multi-scale extraction exploiting divide-and-concatenate in channel dimension is proposed improve representation ability maps. To obtain accurate information, design dual-attention strengthen important spatial regions adaptively. Moreover, aggregate fuse former processed via fusion assist training Extensive experiments CIFAR-10, CIFAR-100, CINIC-10 show that MFEF transfers beneficial outperforms alternative various network architectures.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Face Verification with Multi-Task and Multi-Scale Feature Fusion

Face verification for unrestricted faces in the wild is a challenging task. This paper proposes a method based on two deep convolutional neural networks (CNN) for face verification. In this work, we explore using identification signals to supervise one CNN and the combination of semi-verification and identification to train the other one. In order to estimate semi-verification loss at a low com...

متن کامل

Multi-Layer Model Based on Multi-Scale and Multi-Feature Fusion for SAR Images

A multi-layer classification approach based on multi-scales and multi-features (ML–MFM) for synthetic aperture radar (SAR) images is proposed in this paper. Firstly, the SAR image is partitioned into superpixels, which are local, coherent regions that preserve most of the characteristics necessary for extracting image information. Following this, a new sparse representation-based classification...

متن کامل

An Optimized PatchMatch for multi-scale and multi-feature label fusion

Automatic segmentation methods are important tools for quantitative analysis of Magnetic Resonance Images (MRI). Recently, patch-based label fusion approaches have demonstrated state-of-the-art segmentation accuracy. In this paper, we introduce a new patch-based label fusion framework to perform segmentation of anatomical structures. The proposed approach uses an Optimized PAtchMatch Label fusi...

متن کامل

Design strategies for direct multi-scale and multi-orientation feature extraction in the log-polar domain

Despite the well known advantages that a space-variant representation of the visual signal offers, the required adaptation of the algorithms developed in the Cartesian domain, before applying them in the log-polar space, has limited a wide use of such representation in visual processing applications. In this paper, we present a set of original rules for designing a discrete log-polar mapping th...

متن کامل

Learning natural scene categories by selective multi-scale feature extraction

0262-8856/$ see front matter 2009 Elsevier B.V. A doi:10.1016/j.imavis.2009.11.007 * Corresponding author. Tel.: +39 045 8027803; fax E-mail addresses: [email protected] (A. Pe (M. Cristani), [email protected] (V. Murino). 1 Tel.: +39 045 8027988. 2 Tel.: +39 045 8027996. Natural scene categorization from images represents a very useful task for automatic image analysis systems....

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Lecture Notes in Computer Science

سال: 2022

ISSN: ['1611-3349', '0302-9743']

DOI: https://doi.org/10.1007/978-3-031-15937-4_11