Multi-Scale Dense Networks for Resource Efficient Image Classification

By Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, L. V. D. van der Maaten, Kilian Q. Weinberger. 2017

900 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (2019, background): “Along similar lines, Multi-Scale Dense Networks (MSDNets) (Huang et al., 2018) use information across scales.”
Consistent Accelerated Inference via Confident Adaptive Transformers (2021, background): “[18] Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, and Kilian Weinberger.”
Dynamic Neural Networks: A Survey (2021, methodology): “allowing ”easy” samples to be output at shallow exits without executing deeper layers [12], [45], [46]; or 2) layer skipping, i.”
The Right Tool for the Job: Matching Model and Instance Complexities (2020, methodology): “Larger batch sizes can be applied using methods such as budgeted batch classification (Huang et al., 2018), which specify a budget for the batch and select a subset of the instances to fit that budget, while performing early exit for”
Depth-Adaptive Transformer (2019, methodology): “We also extend the resource efﬁcient object classiﬁcation work of Huang et al. (2017) to structured prediction where dynamic computation decisions impact future computation.”
Graph HyperNetworks for Neural Architecture Search (2018, methodology): “Figure 3 shows a comparison with the various methods presented by Huang et al. (2018).”
Learned Video Compression (2018, methodology): “Specifically, we combine the multiscale rendition [19] of DenseNet [20] with dual path [9].”
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference (2020, positive): “Our work is inspired by Cambazoglu et al. (2010), Teerapittayanon et al. (2017), and Huang et al. (2018), but mainly differs from previous work in that we focus on improving model efﬁciency with minimal quality degradation.”
Slimmable Neural Networks (2018, background): “Huang et al. (2017) adapt early-exits into networks and connect them with dense connectivity.”
Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation (2019, background): “Another extension of the layer-wise dropout solution is to design early-exiting prediction branches to reduce the average execution depth in inference [17, 1, 35, 23].”
Measuring and Narrowing the Compositionality Gap in Language Models (2022, background): “…problems has been previously explored in both language (Graves, 2016; Seo et al., 2017; Dong et al., 2019; Schwartz et al., 2020; Schwarzschild et al., 2021; Nye et al., 2021; Wei et al., 2022b; Zhou et al., 2022) and vision (Bolukbasi et al., 2017; Huang et al., 2018; Wang et al., 2018, 2021).”
Universally Slimmable Networks and Improved Training Techniques (2019, background): “Among these applications, many are required to deploy trained models across different devices or hardware versions [1, 10, 11].”