Fig. 2

Download original image
Multi-head HSA mechanism. Left panel: HSA mechanism, corresponding to the blue box in the right panel (multi-head HSA). In this mechanism, Q, K, and V, represent the query, key, and value, respectively, and were obtained by applying different linear projections to the input, and their dimensions are all d* = 64 in this paper. Softmax is a mathematical function that converts a vector of numbers into a vector of probabilities. ⊙ represents the Hadamard Product. Scale is used to scale the calculated attention scores. Enhanced softmax is an improved version of the softmax function proposed by us. In the right panel, the linear layer represents a linear projection, X represents the input, and different Qi, Ki, Vi are obtained through the linear layer, where i indicates the index of the “head”. The “Concat” operation concatenates features from different heads and then the final result is output through the linear layer.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.