Recursive Multi-Scale Channel-Spatial Attention for Fine-Grained Image Classification

نویسندگان

چکیده

Fine-grained image classification is a difficult problem, and previous studies mainly overcome this problem by locating multiple discriminative regions in different scales then aggregating complementary information explored from the located regions. However, introduces heavy overhead not suitable for real-world application. In paper, we propose recursive multi-scale channel-spatial attention module (RMCSAM) addressing problem. Following experience of research on fine-grained classification, RMCSAM explores attentional information. recursively refining deep feature maps convolutional neural network (CNN) to better correspond channel-wise spatial-wise attention, instead localizing way, provides lightweight that can be inserted into standard CNNs. Experimental results show improve accuracy capturing ability over baselines. Also, performs than other state-of-the-art modules some approaches classification. Code available at https://github.com/Dichao-Liu/Recursive-Multi-Scale-Channel-Spatial-Attention-Module.

برای دانلود رایگان 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

Attention for Fine-Grained Categorization

This paper presents experiments extending the work of Ba et al. (2014) on recurrent neural models for attention into less constrained visual environments, beginning with fine-grained categorization on the Stanford Dogs data set. In this work we use an RNN of the same structure but substitute a more powerful visual network and perform large-scale pre-training of the visual network outside of the...

متن کامل

Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval

Here we offer a more detailed description of the proposed model to facilitate re-implementation. A schematic illustration of the network architecture of the proposed model can be found in Fig. 2 of the main paper. It shows that the model is a Siamese triplet network with three branches of identical architectures and shared parameters. In this section, we further describe the detailed network ar...

متن کامل

Hierarchical Metric Learning for Fine Grained Image Classification

This paper deals with the problem of fine-grained image classification and introduces the notion of hierarchical metric learning for the same. It is indeed challenging to categorize fine-grained image classes merely in terms of a single level classifier given the subtle inter-class visual differences. In order to tackle this problem, we propose a two stage framework where i) the image categorie...

متن کامل

Object-centric Sampling for Fine-grained Image Classification

This paper proposes to go beyond the state-of-the-art deep convolutional neural network (CNN) by incorporating the information from object detection, focusing on dealing with fine-grained image classification. Unfortunately, CNN suffers from over-fiting when it is trained on existing finegrained image classification benchmarks, which typically only consist of less than a few tens of thousands t...

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: IEICE Transactions on Information and Systems

سال: 2022

ISSN: ['0916-8532', '1745-1361']

DOI: https://doi.org/10.1587/transinf.2021edp7166