AFINet: Attentive Feature Integration Networks for Image Classification
Not on the map. Why?
Abstract (arXiv)
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification. Recent advanced models in CNNs, such as ResNets, mainly focus on the skip connection to avoid gradient vanishing. DenseNet designs suggest creating additional bypasses to transfer features as an alternative strategy in network design. In this paper, we design Attentive Feature Integration (AFI) modules, which are widely applicable to most recent network architectures, leading to new architectures named AFI-Nets. AFI-Nets explicitly model the correlations among different levels of features and selectively transfer features with a little overhead.AFI-ResNet-152 obtains a 1.24% relative improvement on the ImageNet dataset while decreases the FLOPs by about 10% and the number of parameters by about 9.2% compared to ResNet-152.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 38 of its 52 references that are in the map. First posted on arXiv 10 May 2021.
Builds on
38 of 52 references.
References · 38
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2014Going Deeper with Convolutionscited by 4,241
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
- 2018CBAM: Convolutional Block Attention Modulecited by 2,477
- 2017Non-local Neural Networkscited by 2,293
26 more
- 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
- 2014How transferable are features in deep neural networks?cited by 1,225
- 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
- 2020Designing Network Design Spacescited by 960
- 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
- 2020ResNeSt: Split-Attention Networkscited by 445
- 2019Selective Kernel Networkscited by 403
- 2017Residual Attention Network for Image Classificationcited by 386
- 2019Learning Deep Transformer Models for Machine Translationcited by 309
- 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
- 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
- 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
- 2020Learning in the Frequency Domaincited by 198
- 2020FcaNet: Frequency Channel Attention Networkscited by 179
- 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
- 2018Gather-Excite: Exploiting Feature Context in Convolutional Neural Networkscited by 139
- 2019Deep Learning on Image Denoising: An overviewcited by 128
- 2017Dual Path Networkscited by 119
- 2018On the importance of single directions for generalizationcited by 99
- 2014Salient Object Detection: A Discriminative Regional Feature Integration Approachcited by 89
- 2017Multi-level Residual Networks from Dynamical Systems Viewcited by 59
- 2018SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networkscited by 55
- 2021RegNet: Self-Regulated Network for Image Classificationcited by 44
- 2017Memory-Efficient Implementation of DenseNetscited by 17
- 2018Mixed Link Networkscited by 10
Built on by
Citing papers per year: 2022: 1.
1 paper.