Local Features and Visual Words Emerge in Activations
This method improves image retrieval accuracy for computer vision applications, though it is incremental as it builds on existing global pooling techniques.
The paper tackles image retrieval by introducing deep spatial matching (DSM), which uses convolutional neural network activations to approximate local features without network modifications or training, achieving state-of-the-art performance on standard benchmarks.
We propose a novel method of deep spatial matching (DSM) for image retrieval. Initial ranking is based on image descriptors extracted from convolutional neural network activations by global pooling, as in recent state-of-the-art work. However, the same sparse 3D activation tensor is also approximated by a collection of local features. These local features are then robustly matched to approximate the optimal alignment of the tensors. This happens without any network modification, additional layers or training. No local feature detection happens on the original image. No local feature descriptors and no visual vocabulary are needed throughout the whole process. We experimentally show that the proposed method achieves the state-of-the-art performance on standard benchmarks across different network architectures and different global pooling methods. The highest gain in performance is achieved when diffusion on the nearest-neighbor graph of global descriptors is initiated from spatially verified images.