HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval

arXiv:2405.07524v1 Announce Type: new
Abstract: Deep image hashing aims to map input images into simple binary hash codes via deep neural networks and thus enable effective large-scale image retrieval. Recently, hybrid networks that combine convolution and Transformer have achieved superior performance on various computer tasks and have attracted extensive attention from researchers. Nevertheless, the potential benefits of such hybrid networks in image retrieval still need to be verified. To this end, we propose a hybrid convolutional and self-attention deep hashing …

arxiv attention convolutional cs.cv hashing hybrid image retrieval self-attention type