Details

Autor(en) / Beteiligte

• Cakir, Fatih
• He, Kun
• Bargal, Sarah Adel
• Sclaroff, Stan

Titel

Hashing with Mutual Information

Ist Teil von

• IEEE transactions on pattern analysis and machine intelligence, 2019-10, Vol.41 (10), p.2424-2437

Ort / Verlag

United States: IEEE

Erscheinungsjahr

2019

Quelle

IEL

Beschreibungen/Notizen

• Binary vector embeddings enable fast nearest neighbor retrieval in large databases of high-dimensional objects, and play an important role in many practical applications, such as image and video retrieval. We study the problem of learning binary vector embeddings under a supervised setting, also known as hashing. We propose a novel supervised hashing method based on optimizing an information-theoretic quantity, mutual information. We show that optimizing mutual information can reduce ambiguity in the induced neighborhood structure in the learned Hamming space, which is essential in obtaining high retrieval performance. To this end, we optimize mutual information in deep neural networks with minibatch stochastic gradient descent, with a formulation that maximally and efficiently utilizes available supervision. Experiments on four image retrieval benchmarks, including ImageNet, confirm the effectiveness of our method in learning high-quality binary embeddings for nearest neighbor retrieval.