Online Residual Quantization Via Streaming Data Correlation Preserving
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2021.3062480
Abstract: Recently, the online retrieval task has been receiving widespread attention, which is closely related to many real-world applications. However, existing online retrieval methods based on hashing suffer from two main problems: a) the models tend… read more here.
Keywords: streaming data; online residual; quantization; quantization via ... See more keywords
Residual Quantization for Low Bit-Width Neural Networks
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2021.3124095
Abstract: Neural network quantization has shown to be an effective way for network compression and acceleration. However, existing binary or ternary quantization methods suffer from two major issues. First, low bit-width input/activation quantization easily results in… read more here.
Keywords: network; residual quantization; quantization; low bit ... See more keywords