What Is Considered Complete for Visual Recognition?
Not on the map. Why?
Abstract (arXiv)
This is an opinion paper. We hope to deliver a key message that current visual recognition systems are far from complete, i.e., recognizing everything that human can recognize, yet it is very unlikely that the gap can be bridged by continuously increasing human annotations. Based on the observation, we advocate for a new type of pre-training task named learning-by-compression. The computational models (e.g., a deep network) are optimized to represent the visual data using compact features, and the features preserve the ability to recover the original data. Semantic annotations, when available, play the role of weak supervision. An important yet challenging issue is the evaluation of image recovery, where we suggest some design principles and future research directions. We hope our proposal can inspire the community to pursue the compression-recovery tradeoff rather than the accuracy-complexity tradeoff.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 45 of its 76 references that are in the map. First posted on arXiv 28 May 2021.
Builds on
45 of 76 references.
References · 45
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Mask R-CNNcited by 7,277
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
33 more
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
- 2014Going Deeper with Convolutionscited by 4,241
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
- 2020Supervised Contrastive Learningcited by 2,829
- 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
- 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
- 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
- 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
- 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
- 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
- 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
- 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
- 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
- 2020In-Domain GAN Inversion for Real Image Editingcited by 420
- 2021GAN Inversion: A Surveycited by 367
- 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 360
- 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
- 2016FractalNet: Ultra-Deep Neural Networks without Residualscited by 216
- 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 206
- 2021Self-supervised Pretraining of Visual Features in the Wildcited by 198
- 2017Colorization as a Proxy Task for Visual Understandingcited by 175
- 2021How to represent part-whole hierarchies in a neural networkcited by 123
- 2017Representation Learning by Learning to Countcited by 120
- 2018The Description Length of Deep Learning Modelscited by 72
- 2017Learning to Segment Every Thingcited by 65
- 2018Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learningcited by 51
- 2020Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gapcited by 50
- 2016Towards Conceptual Compressioncited by 36
- 2018Deep Nets: What have they ever done for Vision?cited by 23
- 2020Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representationscited by 9
- 2018Associative Compression Networks for Representation Learningcited by 4
Built on by
Citing papers per year: 2022: 1; 2023: 2.
3 papers.