Abstract
Token pruning in Swin transformer architectures is provided via identifying initial windows into which the tokenized input to a Swin transformer architecture is divided and a pruning target; identifying D1 tokens in each initial window, excluding those tokens located in a first row of each initial window, having a lowest information content; merging each of the D1 tokens in each initial window into another token in that initial window in a vertical direction to transform each initial window into a corresponding intermediate window; identifying D2 tokens in each intermediate window, excluding those tokens located in a first column of each intermediate window, having a lowest information content; merging each of the D2 tokens in each intermediate window into another token in that intermediate window in a horizontal direction to transform each intermediate window into a corresponding spatially complete window.
Original language | English |
---|---|
Patent number | US2024221375 |
IPC | G06V 10/ 94 A I |
Priority date | 29/12/23 |
Publication status | Published - 4 Jul 2024 |