Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions
Not on the map. Why?
Abstract (arXiv)
Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence. It has great fundamental importance and strong industrial needs. Deep neural networks (DNNs) have largely boosted their performances on many concrete tasks, with the help of large amounts of training data and new powerful computation resources. Though recognition accuracy is usually the first concern for new progresses, efficiency is actually rather important and sometimes critical for both academic research and industrial applications. Moreover, insightful views on the opportunities and challenges of efficiency are also highly required for the entire community. While general surveys on the efficiency issue of DNNs have been done from various perspectives, as far as we are aware, scarcely any of them focused on visual recognition systematically, and thus it is unclear which progresses are applicable to it and what else should be concerned. In this paper, we present the review of the recent advances with our suggestions on the new possible directions towards improving the efficiency of DNN-related visual recognition approaches. We investigate not only from the model but also the data point of view (which is not the case in existing surveys), and focus on three most studied data types (images, videos and points). This paper attempts to provide a systematic summary via a comprehensive survey which can serve as a valuable reference and inspire both researchers and practitioners who work on visual recognition problems.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 259 of its 404 references that are in the map. First posted on arXiv 30 Aug 2021.
Builds on
259 of 404 references.
References · 259
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2014Going Deeper with Convolutionscited by 4,241
- 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
38 more
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
- 2015Learning Deep Features for Discriminative Localizationcited by 2,436
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
- 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
- 2016Identity Mappings in Deep Residual Networkscited by 1,965
- 2018DARTS: Differentiable Architecture Searchcited by 1,798
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
- 2017Deformable Convolutional Networkscited by 1,488
- 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
- 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
- 2017Mixed Precision Trainingcited by 1,156
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
- 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
- 2019Event-based Vision: A Surveycited by 1,016
- 2018Variational image compression with a scale hyperpriorcited by 935
- 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
- 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
- 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
- 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
- 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
- 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
- 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
- 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
- 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
- 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
- 2013Network In Networkcited by 605
- 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 603
- 2018Rethinking the Value of Network Pruningcited by 599
- 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
- 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
- 2018Do Better ImageNet Models Transfer Better?cited by 565
- 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 553
50 most cited of 259 All 259 (JSON)
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.