Learning to Hash with Binary Deep Neural Network
This work addresses the challenge of optimizing non-smooth objectives in binary hashing for applications like image retrieval, but it is incremental as it builds on existing methods with specific improvements.
The authors tackled the problem of learning binary hash codes with deep neural networks by proposing a novel network design that directly outputs binary codes and incorporating constraints for independence, balance, and similarity preservation, resulting in methods that perform favorably compared to state-of-the-art on three benchmark datasets.
This work proposes deep network models and learning algorithms for unsupervised and supervised binary hashing. Our novel network design constrains one hidden layer to directly output the binary codes. This addresses a challenging issue in some previous works: optimizing non-smooth objective functions due to binarization. Moreover, we incorporate independence and balance properties in the direct and strict forms in the learning. Furthermore, we include similarity preserving property in our objective function. Our resulting optimization with these binary, independence, and balance constraints is difficult to solve. We propose to attack it with alternating optimization and careful relaxation. Experimental results on three benchmark datasets show that our proposed methods compare favorably with the state of the art.