Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
arXiv:2008.09662 · doi:10.1109/TIP.2020.3005508
Abstract
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem.To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.
References in corpus (17)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Conditional Image Generation with PixelCNN Decoders
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Conditional Adversarial Domain Adaptation
- End-to-end Optimized Image Compression
- Video Salient Object Detection via Fully Convolutional Networks
- Joint Autoregressive and Hierarchical Priors for Learned Image Compression
- Rigid-Motion Scattering for Texture Classification
- Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
- Conditional Computation in Neural Networks for faster models
- Discrete Variational Autoencoders
- Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos