Embarrassingly Simple Binary Representation Learning
arXiv:1908.09573
Abstract
Recent binary representation learning models usually require sophisticated binary optimization, similarity measure or even generative models as auxiliaries. However, one may wonder whether these non-trivial components are needed to formulate practical and effective hashing models. In this paper, we answer the above question by proposing an embarrassingly simple approach to binary representation learning. With a simple classification objective, our model only incorporates two additional fully-connected layers onto the top of an arbitrary backbone network, whilst complying with the binary constraints during training. The proposed model lower-bounds the Information Bottleneck (IB) between data samples and their semantics, and can be related to many recent `learning to hash' paradigms. We show that, when properly designed, even such a simple network can generate effective binary codes, by fully exploring data semantics without any held-out alternating updating steps or auxiliary models. Experiments are conducted on conventional large-scale benchmarks, i.e., CIFAR-10, NUS-WIDE, and ImageNet, where the proposed simple model outperforms the state-of-the-art methods.
arXiv commentICCV 2019 CEFRL4 Workshop
References in corpus (9)
- Auto-Encoding Variational Bayes
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- The information bottleneck method
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
- Learning Deep Embeddings with Histogram Loss
- Binary Generative Adversarial Networks for Image Retrieval
- BinGAN: Learning Compact Binary Descriptors with a Regularized GAN
- Zero-Shot Hashing via Transferring Supervised Knowledge
Cited by in corpus (5)
- A Decade Survey of Content Based Image Retrieval using Deep Learning
- One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
- Auto-Encoding Twin-Bottleneck Hashing
- BiDet: An Efficient Binarized Object Detector
- Shuffle and Learn: Minimizing Mutual Information for Unsupervised Hashing