Learning Binary Codes and Binary Weights for Efficient Classification

by   Fumin Shen, et al.

This paper proposes a generic formulation that significantly expedites the training and deployment of image classification models, particularly under the scenarios of many image categories and high feature dimensions. As a defining property, our method represents both the images and learned classifiers using binary hash codes, which are simultaneously learned from the training data. Classifying an image thereby reduces to computing the Hamming distance between the binary codes of the image and classifiers and selecting the class with minimal Hamming distance. Conventionally, compact hash codes are primarily used for accelerating image search. Our work is first of its kind to represent classifiers using binary codes. Specifically, we formulate multi-class image classification as an optimization problem over binary variables. The optimization alternatively proceeds over the binary classifiers and image hash codes. Profiting from the special property of binary codes, we show that the sub-problems can be efficiently solved through either a binary quadratic program (BQP) or linear program. In particular, for attacking the BQP problem, we propose a novel bit-flipping procedure which enjoys high efficacy and local optimality guarantee. Our formulation supports a large family of empirical loss functions and is here instantiated by exponential / hinge losses. Comprehensive evaluations are conducted on several representative image benchmarks. The experiments consistently observe reduced complexities of model training and deployment, without sacrifice of accuracies.


page 1

page 2

page 3

page 4


Optimal Binary Linear Codes from Maximal Arcs

The binary Hamming codes with parameters [2^m-1, 2^m-1-m, 3] are perfect...

Error Correction Maximization for Deep Image Hashing

We propose to use the concept of the Hamming bound to derive the optimal...

Supervised Incremental Hashing

We propose an incremental strategy for learning hash functions with kern...

Efficient Querying from Weighted Binary Codes

Binary codes are widely used to represent the data due to their small st...

Learning to Rank Binary Codes

Binary codes have been widely used in vision problems as a compact featu...

Projected Hamming Dissimilarity for Bit-Level Importance Coding in Collaborative Filtering

When reasoning about tasks that involve large amounts of data, a common ...

Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation

Speech enhancement tasks have seen significant improvements with the adv...

Please sign up or login with your details

Forgot password? Click here to reset