Abstract: A technique for improving the computational time for performing a non-maximum suppression operation may include receiving a request to perform a non-maximum suppression operation on a set of candidate predictions of a computing task, and performing a statistical analysis on a set of confidence scores corresponding to the set of candidate predictions to determine a standard deviation of the set of confidence scores. A confidence score threshold can be determined based on the standard deviation. Candidate predictions having a confidence score below the confidence score threshold can then be discarded to form a reduced set of candidate predictions. Additional candidate predictions can be discarded from the reduced set of candidate predictions based on an intersection-over-union overlap metric, and the remaining candidate predictions from the reduced set of candidate predictions can be provided as a result of the non-maximum suppression operation.

Abstract: Provided are a proposals processing method and related products for object detection, where the method comprising: determining a score threshold according to a statistics property of scores of a first quantity of proposal; selecting a second quantity of proposals with a score higher than the score threshold from the first quantity of proposals; and suppressing to the second quantity of proposals to get a third quantity of non-overlapping proposals with high scores, as such, time complexity for selecting a second quantity of proposals is reduced, and efficiency for selection of the proposals to be used for suppression is improved, thereby improving proposal processing efficiency and object detection efficiency.

Abstract: Provided are a proposals processing method and related products for object detection, where the method comprising: determining a score threshold according to a statistics property of scores of a first quantity of proposal; selecting a second quantity of proposals with a score higher than the score threshold from the first quantity of proposals; and suppressing to the second quantity of proposals to get a third quantity of non-overlapping proposals with high scores, as such, time complexity for selecting a second quantity of proposals is reduced, and efficiency for selection of the proposals to be used for suppression is improved, thereby improving proposal processing efficiency and object detection efficiency.