What does "iof" mean?

In the file max_iou_assigner, this line:

class MaxIoUAssigner(BaseAssigner):
    """Assign a corresponding gt bbox or background to each bbox.

    Each proposals will be assigned with `-1`, `0`, or a positive integer
    indicating the ground truth index.

    - -1: don't care
    - 0: negative sample, no assigned gt
    - positive integer: positive sample, index (1-based) of assigned gt

    Args:
        pos_iou_thr (float): IoU threshold for positive bboxes.
        neg_iou_thr (float or tuple): IoU threshold for negative bboxes.
        min_pos_iou (float): Minimum iou for a bbox to be considered as a
            positive bbox. Positive samples can have smaller IoU than
            pos_iou_thr due to the 4th step (assign max IoU sample to each gt).
        gt_max_assign_all (bool): Whether to assign all bboxes with the same
            highest overlap with some gt to that gt.
        ignore_iof_thr (float): IoF threshold for ignoring bboxes (if
            `gt_bboxes_ignore` is specified). Negative values mean not
            ignoring any bboxes.
        ignore_wrt_candidates (bool): Whether to compute the iof between
            `bboxes` and `gt_bboxes_ignore`, or the contrary.
    """

what does ‘IoF’ mean?

[hajlyx]

IoU is used most of the time. I think that IoF may be used in NMS processing, for example, you’ve got two detection bboxes of ‘person’ class, one bbox surrounded person completely and another surrounded only upper part of the same person, in this situation the IoU may be less than 0.5 but IoF is 1.0, choosing IoU>0.5 as the threshold may not suppress duplicate bbox and IoF>0.5 works well.

[hellock]

@Flawless1202 It is intersection over foreground, just as @hajlyx replied. See here for more details. We use iof instead of iou for ignored regions, you can just refer to the implementation of assigner.