Comparative evaluation of CNN architectures for Image Caption Generation
Not on the map. Why?
Abstract (arXiv)
Aided by recent advances in Deep Learning, Image Caption Generation has seen tremendous progress over the last few years. Most methods use transfer learning to extract visual information, in the form of image features, with the help of pre-trained Convolutional Neural Network models followed by transformation of the visual information using a Caption Generator module to generate the output sentences. Different methods have used different Convolutional Neural Network Architectures and, to the best of our knowledge, there is no systematic study which compares the relative efficacy of different Convolutional Neural Network architectures for extracting the visual information. In this work, we have evaluated 17 different Convolutional Neural Networks on two popular Image Caption Generation frameworks: the first based on Neural Image Caption (NIC) generation model and the second based on Soft-Attention framework. We observe that model complexity of Convolutional Neural Network, as measured by number of parameters, and the accuracy of the model on Object Recognition task does not necessarily co-relate with its efficacy on feature extraction for Image Caption Generation task.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 23 Feb 2021.
Builds on
31 of 42 references.
References · 31
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2014Going Deeper with Convolutionscited by 4,231
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
19 more
- 2016Wide Residual Networkscited by 3,057
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
- 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
- 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
- 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
- 2017Convolutional Sequence to Sequence Learningcited by 550
- 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 213
- 2017Dual Path Networkscited by 119
- 2016Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challengecited by 116
- 2014Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)cited by 94
- 2019Multimodal Transformer with Multi-View Visual Representation for Image Captioningcited by 86
- 2017Convolutional Image Captioningcited by 52
- 2016PolyNet: A Pursuit of Structural Diversity in Very Deep Networkscited by 38
- 2016Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measurescited by 36
Built on by
Citing papers per year: 2021: 3.
3 papers.