Build A Faster Image Search
Post · Apr 5, 2017 22:20 ·
Want to build a faster / better image search? Combine your hashing and aggregating systems. Or at least that’s the advice from a new paper out of Baidu research yesterday. The storage space needed gets a bit larger, but you reap the benefits of a much faster lookup.
Highlights From The Paper
- “Takes the local (embedded) features as inputs and learn the aggregation and hashing function simultaneously.”
- “When increasing the code length, SAH outperforms compared methods a large margin.”
- “For aggregating, we rely on the state-of-the-art Generalized Max Pooling.”
- “For hashing, we propose a relaxed version of Binary Autoencoder.”
- Thanh-Toan Do
- Dang-Khoa Le Tan
- Trung T. Pham
- Ngai-Man Cheung
In most state-of-the-art hashing-based visual search systems, local image descriptors of an image are first aggregated as a single feature vector. This feature vector is then subjected to a hashing function that produces a binary hash code. In previous work, the aggregating and the hashing processes are designed independently. In this paper, we propose a novel framework where feature aggregating and hashing are designed simultaneously and optimized jointly. Specifically, our joint optimization produces aggregated representations that can be better reconstructed by some binary codes. This leads to more discriminative binary hash codes and improved retrieval accuracy. In addition, we also propose a fast version of the recently-proposed Binary Autoencoder to be used in our proposed framework. We perform extensive retrieval experiments on several benchmark datasets with both SIFT and convolutional features. Our results suggest that the proposed framework achieves significant improvements over the state of the art.
Read the paper (pdf) »