What Is Considered Complete for Visual Recognition?
arXiv:2105.13978
Abstract
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.
13 pages, 5 figures, 1 table
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- Bootstrap your own latent: A new approach to self-supervised Learning
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
- High-Performance Large-Scale Image Recognition Without Normalization
- Self-supervised Pretraining of Visual Features in the Wild
- Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
- Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations