diff --git a/torchvision/datasets/vision.py b/torchvision/datasets/vision.py
index cd4399c6c79..fc01798c9e6 100644
--- a/torchvision/datasets/vision.py
+++ b/torchvision/datasets/vision.py
@@ -35,7 +35,7 @@ def __init__(
         transform: Optional[Callable] = None,
         target_transform: Optional[Callable] = None,
     ) -> None:
-        _log_api_usage_once("datasets", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         if isinstance(root, torch._six.string_classes):
             root = os.path.expanduser(root)
         self.root = root
diff --git a/torchvision/models/alexnet.py b/torchvision/models/alexnet.py
index ae36054386f..0f88ecb8a5e 100644
--- a/torchvision/models/alexnet.py
+++ b/torchvision/models/alexnet.py
@@ -18,7 +18,7 @@
 class AlexNet(nn.Module):
     def __init__(self, num_classes: int = 1000, dropout: float = 0.5) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.features = nn.Sequential(
             nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
             nn.ReLU(inplace=True),
diff --git a/torchvision/models/densenet.py b/torchvision/models/densenet.py
index 289c027f94d..6ff63d3f53f 100644
--- a/torchvision/models/densenet.py
+++ b/torchvision/models/densenet.py
@@ -163,7 +163,7 @@ def __init__(
     ) -> None:
 
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         # First convolution
         self.features = nn.Sequential(
diff --git a/torchvision/models/detection/generalized_rcnn.py b/torchvision/models/detection/generalized_rcnn.py
index b92f8637d6d..5537be3a8e6 100644
--- a/torchvision/models/detection/generalized_rcnn.py
+++ b/torchvision/models/detection/generalized_rcnn.py
@@ -27,7 +27,7 @@ class GeneralizedRCNN(nn.Module):
 
     def __init__(self, backbone: nn.Module, rpn: nn.Module, roi_heads: nn.Module, transform: nn.Module) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.transform = transform
         self.backbone = backbone
         self.rpn = rpn
diff --git a/torchvision/models/detection/retinanet.py b/torchvision/models/detection/retinanet.py
index d123f5bd6ff..c4b9f9555de 100644
--- a/torchvision/models/detection/retinanet.py
+++ b/torchvision/models/detection/retinanet.py
@@ -337,7 +337,7 @@ def __init__(
         topk_candidates=1000,
     ):
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         if not hasattr(backbone, "out_channels"):
             raise ValueError(
diff --git a/torchvision/models/detection/ssd.py b/torchvision/models/detection/ssd.py
index 5df8138ecef..8052225173b 100644
--- a/torchvision/models/detection/ssd.py
+++ b/torchvision/models/detection/ssd.py
@@ -182,7 +182,7 @@ def __init__(
         positive_fraction: float = 0.25,
     ):
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         self.backbone = backbone
 
diff --git a/torchvision/models/detection/ssdlite.py b/torchvision/models/detection/ssdlite.py
index f434a865763..02d92735f37 100644
--- a/torchvision/models/detection/ssdlite.py
+++ b/torchvision/models/detection/ssdlite.py
@@ -120,7 +120,7 @@ def __init__(
         min_depth: int = 16,
     ):
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         assert not backbone[c4_pos].use_res_connect
         self.features = nn.Sequential(
diff --git a/torchvision/models/efficientnet.py b/torchvision/models/efficientnet.py
index 249e2400f63..e0d0af05af4 100644
--- a/torchvision/models/efficientnet.py
+++ b/torchvision/models/efficientnet.py
@@ -170,7 +170,7 @@ def __init__(
             norm_layer (Optional[Callable[..., nn.Module]]): Module specifying the normalization layer to use
         """
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         if not inverted_residual_setting:
             raise ValueError("The inverted_residual_setting should not be empty")
diff --git a/torchvision/models/googlenet.py b/torchvision/models/googlenet.py
index 476da0d8a53..f98e2109e27 100644
--- a/torchvision/models/googlenet.py
+++ b/torchvision/models/googlenet.py
@@ -39,7 +39,7 @@ def __init__(
         dropout_aux: float = 0.7,
     ) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         if blocks is None:
             blocks = [BasicConv2d, Inception, InceptionAux]
         if init_weights is None:
diff --git a/torchvision/models/inception.py b/torchvision/models/inception.py
index 85236c6dfb3..35d68beea8b 100644
--- a/torchvision/models/inception.py
+++ b/torchvision/models/inception.py
@@ -37,7 +37,7 @@ def __init__(
         dropout: float = 0.5,
     ) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         if inception_blocks is None:
             inception_blocks = [BasicConv2d, InceptionA, InceptionB, InceptionC, InceptionD, InceptionE, InceptionAux]
         if init_weights is None:
diff --git a/torchvision/models/mnasnet.py b/torchvision/models/mnasnet.py
index bff4e061a72..c657c4fba08 100644
--- a/torchvision/models/mnasnet.py
+++ b/torchvision/models/mnasnet.py
@@ -98,7 +98,7 @@ class MNASNet(torch.nn.Module):
 
     def __init__(self, alpha: float, num_classes: int = 1000, dropout: float = 0.2) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         assert alpha > 0.0
         self.alpha = alpha
         self.num_classes = num_classes
diff --git a/torchvision/models/mobilenetv2.py b/torchvision/models/mobilenetv2.py
index 1e21f299654..a3a41200ec5 100644
--- a/torchvision/models/mobilenetv2.py
+++ b/torchvision/models/mobilenetv2.py
@@ -111,7 +111,7 @@ def __init__(
 
         """
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         if block is None:
             block = InvertedResidual
diff --git a/torchvision/models/mobilenetv3.py b/torchvision/models/mobilenetv3.py
index 306fa8d2b49..13bc88a2041 100644
--- a/torchvision/models/mobilenetv3.py
+++ b/torchvision/models/mobilenetv3.py
@@ -151,7 +151,7 @@ def __init__(
             dropout (float): The droupout probability
         """
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         if not inverted_residual_setting:
             raise ValueError("The inverted_residual_setting should not be empty")
diff --git a/torchvision/models/optical_flow/raft.py b/torchvision/models/optical_flow/raft.py
index 18bf7dbafc3..e466d2fa1f1 100644
--- a/torchvision/models/optical_flow/raft.py
+++ b/torchvision/models/optical_flow/raft.py
@@ -440,7 +440,7 @@ def __init__(self, *, feature_encoder, context_encoder, corr_block, update_block
                 If ``None`` (default), the flow is upsampled using interpolation.
         """
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         self.feature_encoder = feature_encoder
         self.context_encoder = context_encoder
diff --git a/torchvision/models/regnet.py b/torchvision/models/regnet.py
index 417054fe547..a6bf59d3037 100644
--- a/torchvision/models/regnet.py
+++ b/torchvision/models/regnet.py
@@ -310,7 +310,7 @@ def __init__(
         activation: Optional[Callable[..., nn.Module]] = None,
     ) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         if stem_type is None:
             stem_type = SimpleStemIN
diff --git a/torchvision/models/resnet.py b/torchvision/models/resnet.py
index d7dd3480ff6..67d1575bbbc 100644
--- a/torchvision/models/resnet.py
+++ b/torchvision/models/resnet.py
@@ -174,7 +174,7 @@ def __init__(
         norm_layer: Optional[Callable[..., nn.Module]] = None,
     ) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         if norm_layer is None:
             norm_layer = nn.BatchNorm2d
         self._norm_layer = norm_layer
diff --git a/torchvision/models/segmentation/_utils.py b/torchvision/models/segmentation/_utils.py
index 209a7a57c26..172bcc379ab 100644
--- a/torchvision/models/segmentation/_utils.py
+++ b/torchvision/models/segmentation/_utils.py
@@ -13,7 +13,7 @@ class _SimpleSegmentationModel(nn.Module):
 
     def __init__(self, backbone: nn.Module, classifier: nn.Module, aux_classifier: Optional[nn.Module] = None) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.backbone = backbone
         self.classifier = classifier
         self.aux_classifier = aux_classifier
diff --git a/torchvision/models/segmentation/lraspp.py b/torchvision/models/segmentation/lraspp.py
index 77243822434..9650e550e97 100644
--- a/torchvision/models/segmentation/lraspp.py
+++ b/torchvision/models/segmentation/lraspp.py
@@ -38,7 +38,7 @@ def __init__(
         self, backbone: nn.Module, low_channels: int, high_channels: int, num_classes: int, inter_channels: int = 128
     ) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.backbone = backbone
         self.classifier = LRASPPHead(low_channels, high_channels, num_classes, inter_channels)
 
diff --git a/torchvision/models/shufflenetv2.py b/torchvision/models/shufflenetv2.py
index 9bec542d6f5..9032db7c62f 100644
--- a/torchvision/models/shufflenetv2.py
+++ b/torchvision/models/shufflenetv2.py
@@ -100,7 +100,7 @@ def __init__(
         inverted_residual: Callable[..., nn.Module] = InvertedResidual,
     ) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
 
         if len(stages_repeats) != 3:
             raise ValueError("expected stages_repeats as list of 3 positive ints")
diff --git a/torchvision/models/squeezenet.py b/torchvision/models/squeezenet.py
index 6c14c779c0c..8e0cc673e3f 100644
--- a/torchvision/models/squeezenet.py
+++ b/torchvision/models/squeezenet.py
@@ -36,7 +36,7 @@ def forward(self, x: torch.Tensor) -> torch.Tensor:
 class SqueezeNet(nn.Module):
     def __init__(self, version: str = "1_0", num_classes: int = 1000, dropout: float = 0.5) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.num_classes = num_classes
         if version == "1_0":
             self.features = nn.Sequential(
diff --git a/torchvision/models/vgg.py b/torchvision/models/vgg.py
index c96bc5e1d8d..baa07e49595 100644
--- a/torchvision/models/vgg.py
+++ b/torchvision/models/vgg.py
@@ -37,7 +37,7 @@ def __init__(
         self, features: nn.Module, num_classes: int = 1000, init_weights: bool = True, dropout: float = 0.5
     ) -> None:
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.features = features
         self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
         self.classifier = nn.Sequential(
diff --git a/torchvision/models/video/resnet.py b/torchvision/models/video/resnet.py
index 475608886c6..d91a9154993 100644
--- a/torchvision/models/video/resnet.py
+++ b/torchvision/models/video/resnet.py
@@ -209,7 +209,7 @@ def __init__(
             zero_init_residual (bool, optional): Zero init bottleneck residual BN. Defaults to False.
         """
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.inplanes = 64
 
         self.stem = stem()
diff --git a/torchvision/ops/boxes.py b/torchvision/ops/boxes.py
index 537c23480d8..363213eb220 100644
--- a/torchvision/ops/boxes.py
+++ b/torchvision/ops/boxes.py
@@ -34,7 +34,7 @@ def nms(boxes: Tensor, scores: Tensor, iou_threshold: float) -> Tensor:
         Tensor: int64 tensor with the indices of the elements that have been kept
         by NMS, sorted in decreasing order of scores
     """
-    _log_api_usage_once("ops", "nms")
+    _log_api_usage_once("torchvision.ops.boxes.nms")
     _assert_has_ops()
     return torch.ops.torchvision.nms(boxes, scores, iou_threshold)
 
@@ -63,7 +63,7 @@ def batched_nms(
         Tensor: int64 tensor with the indices of the elements that have been kept by NMS, sorted
         in decreasing order of scores
     """
-    _log_api_usage_once("ops", "batched_nms")
+    _log_api_usage_once("torchvision.ops.boxes.batched_nms")
     # Benchmarks that drove the following thresholds are at
     # https://github.com/pytorch/vision/issues/1311#issuecomment-781329339
     if boxes.numel() > (4000 if boxes.device.type == "cpu" else 20000) and not torchvision._is_tracing():
@@ -122,7 +122,7 @@ def remove_small_boxes(boxes: Tensor, min_size: float) -> Tensor:
         Tensor[K]: indices of the boxes that have both sides
         larger than min_size
     """
-    _log_api_usage_once("ops", "remove_small_boxes")
+    _log_api_usage_once("torchvision.ops.boxes.remove_small_boxes")
     ws, hs = boxes[:, 2] - boxes[:, 0], boxes[:, 3] - boxes[:, 1]
     keep = (ws >= min_size) & (hs >= min_size)
     keep = torch.where(keep)[0]
@@ -141,7 +141,7 @@ def clip_boxes_to_image(boxes: Tensor, size: Tuple[int, int]) -> Tensor:
     Returns:
         Tensor[N, 4]: clipped boxes
     """
-    _log_api_usage_once("ops", "clip_boxes_to_image")
+    _log_api_usage_once("torchvision.ops.boxes.clip_boxes_to_image")
     dim = boxes.dim()
     boxes_x = boxes[..., 0::2]
     boxes_y = boxes[..., 1::2]
@@ -182,7 +182,7 @@ def box_convert(boxes: Tensor, in_fmt: str, out_fmt: str) -> Tensor:
         Tensor[N, 4]: Boxes into converted format.
     """
 
-    _log_api_usage_once("ops", "box_convert")
+    _log_api_usage_once("torchvision.ops.boxes.box_convert")
     allowed_fmts = ("xyxy", "xywh", "cxcywh")
     if in_fmt not in allowed_fmts or out_fmt not in allowed_fmts:
         raise ValueError("Unsupported Bounding Box Conversions for given in_fmt and out_fmt")
@@ -232,7 +232,7 @@ def box_area(boxes: Tensor) -> Tensor:
     Returns:
         Tensor[N]: the area for each box
     """
-    _log_api_usage_once("ops", "box_area")
+    _log_api_usage_once("torchvision.ops.boxes.box_area")
     boxes = _upcast(boxes)
     return (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])
 
@@ -268,7 +268,7 @@ def box_iou(boxes1: Tensor, boxes2: Tensor) -> Tensor:
     Returns:
         Tensor[N, M]: the NxM matrix containing the pairwise IoU values for every element in boxes1 and boxes2
     """
-    _log_api_usage_once("ops", "box_iou")
+    _log_api_usage_once("torchvision.ops.boxes.box_iou")
     inter, union = _box_inter_union(boxes1, boxes2)
     iou = inter / union
     return iou
@@ -291,7 +291,7 @@ def generalized_box_iou(boxes1: Tensor, boxes2: Tensor) -> Tensor:
         for every element in boxes1 and boxes2
     """
 
-    _log_api_usage_once("ops", "generalized_box_iou")
+    _log_api_usage_once("torchvision.ops.boxes.generalized_box_iou")
     # degenerate boxes gives inf / nan results
     # so do an early check
     assert (boxes1[:, 2:] >= boxes1[:, :2]).all()
@@ -323,7 +323,7 @@ def masks_to_boxes(masks: torch.Tensor) -> torch.Tensor:
     Returns:
         Tensor[N, 4]: bounding boxes
     """
-    _log_api_usage_once("ops", "masks_to_boxes")
+    _log_api_usage_once("torchvision.ops.boxes.masks_to_boxes")
     if masks.numel() == 0:
         return torch.zeros((0, 4), device=masks.device, dtype=torch.float)
 
diff --git a/torchvision/ops/deform_conv.py b/torchvision/ops/deform_conv.py
index b756274df71..f6bcaf1cc08 100644
--- a/torchvision/ops/deform_conv.py
+++ b/torchvision/ops/deform_conv.py
@@ -61,7 +61,7 @@ def deform_conv2d(
         >>>  torch.Size([4, 5, 8, 8])
     """
 
-    _log_api_usage_once("ops", "deform_conv2d")
+    _log_api_usage_once("torchvision.ops.deform_conv.deform_conv2d")
     _assert_has_ops()
     out_channels = weight.shape[0]
 
diff --git a/torchvision/ops/feature_pyramid_network.py b/torchvision/ops/feature_pyramid_network.py
index e73d1ee853b..3efde8d1f86 100644
--- a/torchvision/ops/feature_pyramid_network.py
+++ b/torchvision/ops/feature_pyramid_network.py
@@ -77,7 +77,7 @@ def __init__(
         extra_blocks: Optional[ExtraFPNBlock] = None,
     ):
         super().__init__()
-        _log_api_usage_once("ops", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.inner_blocks = nn.ModuleList()
         self.layer_blocks = nn.ModuleList()
         for in_channels in in_channels_list:
diff --git a/torchvision/ops/focal_loss.py b/torchvision/ops/focal_loss.py
index d19e7465720..9c0a98a8bb1 100644
--- a/torchvision/ops/focal_loss.py
+++ b/torchvision/ops/focal_loss.py
@@ -32,7 +32,7 @@ def sigmoid_focal_loss(
     Returns:
         Loss tensor with the reduction option applied.
     """
-    _log_api_usage_once("ops", "sigmoid_focal_loss")
+    _log_api_usage_once("torchvision.ops.focal_loss.sigmoid_focal_loss")
     p = torch.sigmoid(inputs)
     ce_loss = F.binary_cross_entropy_with_logits(inputs, targets, reduction="none")
     p_t = p * targets + (1 - p) * (1 - targets)
diff --git a/torchvision/ops/misc.py b/torchvision/ops/misc.py
index 0189d1b140f..2a911f8c446 100644
--- a/torchvision/ops/misc.py
+++ b/torchvision/ops/misc.py
@@ -61,7 +61,7 @@ def __init__(
             warnings.warn("`n` argument is deprecated and has been renamed `num_features`", DeprecationWarning)
             num_features = n
         super().__init__()
-        _log_api_usage_once("ops", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.eps = eps
         self.register_buffer("weight", torch.ones(num_features))
         self.register_buffer("bias", torch.zeros(num_features))
@@ -155,7 +155,7 @@ def __init__(
         if activation_layer is not None:
             layers.append(activation_layer(inplace=inplace))
         super().__init__(*layers)
-        _log_api_usage_once("ops", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.out_channels = out_channels
 
 
@@ -179,7 +179,7 @@ def __init__(
         scale_activation: Callable[..., torch.nn.Module] = torch.nn.Sigmoid,
     ) -> None:
         super().__init__()
-        _log_api_usage_once("ops", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         self.avgpool = torch.nn.AdaptiveAvgPool2d(1)
         self.fc1 = torch.nn.Conv2d(input_channels, squeeze_channels, 1)
         self.fc2 = torch.nn.Conv2d(squeeze_channels, input_channels, 1)
diff --git a/torchvision/ops/poolers.py b/torchvision/ops/poolers.py
index cb3abc70f80..4fd6686a748 100644
--- a/torchvision/ops/poolers.py
+++ b/torchvision/ops/poolers.py
@@ -276,7 +276,7 @@ def __init__(
         canonical_level: int = 4,
     ):
         super().__init__()
-        _log_api_usage_once("ops", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         if isinstance(output_size, int):
             output_size = (output_size, output_size)
         self.featmap_names = featmap_names
diff --git a/torchvision/ops/ps_roi_align.py b/torchvision/ops/ps_roi_align.py
index f24a41866e9..da03aa049d4 100644
--- a/torchvision/ops/ps_roi_align.py
+++ b/torchvision/ops/ps_roi_align.py
@@ -43,7 +43,7 @@ def ps_roi_align(
     Returns:
         Tensor[K, C / (output_size[0] * output_size[1]), output_size[0], output_size[1]]: The pooled RoIs
     """
-    _log_api_usage_once("ops", "ps_roi_align")
+    _log_api_usage_once("torchvision.ops.ps_roi_align.ps_roi_align")
     _assert_has_ops()
     check_roi_boxes_shape(boxes)
     rois = boxes
diff --git a/torchvision/ops/ps_roi_pool.py b/torchvision/ops/ps_roi_pool.py
index 9079aaacc6e..e83280f4747 100644
--- a/torchvision/ops/ps_roi_pool.py
+++ b/torchvision/ops/ps_roi_pool.py
@@ -37,7 +37,7 @@ def ps_roi_pool(
     Returns:
         Tensor[K, C / (output_size[0] * output_size[1]), output_size[0], output_size[1]]: The pooled RoIs.
     """
-    _log_api_usage_once("ops", "ps_roi_pool")
+    _log_api_usage_once("torchvision.ops.ps_roi_pool.ps_roi_pool")
     _assert_has_ops()
     check_roi_boxes_shape(boxes)
     rois = boxes
diff --git a/torchvision/ops/roi_align.py b/torchvision/ops/roi_align.py
index 509c0777d2d..c2ca35433bd 100644
--- a/torchvision/ops/roi_align.py
+++ b/torchvision/ops/roi_align.py
@@ -50,7 +50,7 @@ def roi_align(
     Returns:
         Tensor[K, C, output_size[0], output_size[1]]: The pooled RoIs.
     """
-    _log_api_usage_once("ops", "roi_align")
+    _log_api_usage_once("torchvision.ops.roi_align.roi_align")
     _assert_has_ops()
     check_roi_boxes_shape(boxes)
     rois = boxes
diff --git a/torchvision/ops/roi_pool.py b/torchvision/ops/roi_pool.py
index a8f9c4d2092..c39aed98eb8 100644
--- a/torchvision/ops/roi_pool.py
+++ b/torchvision/ops/roi_pool.py
@@ -39,7 +39,7 @@ def roi_pool(
     Returns:
         Tensor[K, C, output_size[0], output_size[1]]: The pooled RoIs.
     """
-    _log_api_usage_once("ops", "roi_pool")
+    _log_api_usage_once("torchvision.ops.roi_pool.roi_pool")
     _assert_has_ops()
     check_roi_boxes_shape(boxes)
     rois = boxes
diff --git a/torchvision/ops/stochastic_depth.py b/torchvision/ops/stochastic_depth.py
index 40143d06141..61251a3af17 100644
--- a/torchvision/ops/stochastic_depth.py
+++ b/torchvision/ops/stochastic_depth.py
@@ -23,7 +23,7 @@ def stochastic_depth(input: Tensor, p: float, mode: str, training: bool = True)
     Returns:
         Tensor[N, ...]: The randomly zeroed tensor.
     """
-    _log_api_usage_once("ops", "stochastic_depth")
+    _log_api_usage_once("torchvision.ops.stochastic_depth.stochastic_depth")
     if p < 0.0 or p > 1.0:
         raise ValueError(f"drop probability has to be between 0 and 1, but got {p}")
     if mode not in ["batch", "row"]:
diff --git a/torchvision/prototype/models/vision_transformer.py b/torchvision/prototype/models/vision_transformer.py
index 83c8160afc4..c9ac0f42565 100644
--- a/torchvision/prototype/models/vision_transformer.py
+++ b/torchvision/prototype/models/vision_transformer.py
@@ -140,7 +140,7 @@ def __init__(
         norm_layer: Callable[..., torch.nn.Module] = partial(nn.LayerNorm, eps=1e-6),
     ):
         super().__init__()
-        _log_api_usage_once("models", self.__class__.__name__)
+        _log_api_usage_once(self.__class__.__qualname__)
         torch._assert(image_size % patch_size == 0, "Input shape indivisible by patch size!")
         self.image_size = image_size
         self.patch_size = patch_size
diff --git a/torchvision/utils.py b/torchvision/utils.py
index 3a17a46e26e..4e8e203a29e 100644
--- a/torchvision/utils.py
+++ b/torchvision/utils.py
@@ -42,7 +42,7 @@ def make_grid(
     Returns:
         grid (Tensor): the tensor containing grid of images.
     """
-    _log_api_usage_once("utils", "make_grid")
+    _log_api_usage_once("torchvision.utils.make_grid")
     if not (torch.is_tensor(tensor) or (isinstance(tensor, list) and all(torch.is_tensor(t) for t in tensor))):
         raise TypeError(f"tensor or list of tensors expected, got {type(tensor)}")
 
@@ -131,7 +131,7 @@ def save_image(
         **kwargs: Other arguments are documented in ``make_grid``.
     """
 
-    _log_api_usage_once("utils", "save_image")
+    _log_api_usage_once("torchvision.utils.save_image")
     grid = make_grid(tensor, **kwargs)
     # Add 0.5 after unnormalizing to [0, 255] to round to nearest integer
     ndarr = grid.mul(255).add_(0.5).clamp_(0, 255).permute(1, 2, 0).to("cpu", torch.uint8).numpy()
@@ -176,7 +176,7 @@ def draw_bounding_boxes(
         img (Tensor[C, H, W]): Image Tensor of dtype uint8 with bounding boxes plotted.
     """
 
-    _log_api_usage_once("utils", "draw_bounding_boxes")
+    _log_api_usage_once("torchvision.utils.draw_bounding_boxes")
     if not isinstance(image, torch.Tensor):
         raise TypeError(f"Tensor expected, got {type(image)}")
     elif image.dtype != torch.uint8:
@@ -255,7 +255,7 @@ def draw_segmentation_masks(
         img (Tensor[C, H, W]): Image Tensor, with segmentation masks drawn on top.
     """
 
-    _log_api_usage_once("utils", "draw_segmentation_masks")
+    _log_api_usage_once("torchvision.utils.draw_segmentation_masks")
     if not isinstance(image, torch.Tensor):
         raise TypeError(f"The image must be a tensor, got {type(image)}")
     elif image.dtype != torch.uint8:
@@ -333,7 +333,7 @@ def draw_keypoints(
         img (Tensor[C, H, W]): Image Tensor of dtype uint8 with keypoints drawn.
     """
 
-    _log_api_usage_once("utils", "draw_keypoints")
+    _log_api_usage_once("torchvision.utils.draw_keypoints")
     if not isinstance(image, torch.Tensor):
         raise TypeError(f"The image must be a tensor, got {type(image)}")
     elif image.dtype != torch.uint8:
@@ -380,7 +380,9 @@ def _generate_color_palette(num_masks: int):
     return [tuple((i * palette) % 255) for i in range(num_masks)]
 
 
-def _log_api_usage_once(module: str, name: str) -> None:
+def _log_api_usage_once(event: str) -> None:
     if torch.jit.is_scripting() or torch.jit.is_tracing():
         return
-    torch._C._log_api_usage_once(f"torchvision.{module}.{name}")
+    if not event.startswith("torchvision"):
+        return
+    torch._C._log_api_usage_once(event)