EdgeFirst
/

yolo11-det

@@ -105,7 +105,7 @@ Row conventions in the table below:
 - **Rows whose `Δ vs FP32` cell carries a ⚠** are below our accuracy expectations for that platform (more than 10 percentage points under the float reference). The numbers are real measurements on real hardware, reproducible from the linked Studio session, and we publish them as-is; we are investigating the results to make improvements, and the next snapshot of this card will reflect any recovered accuracy.
 - **Edition badges.** A Source cell such as `v-XXXX · 2026 Q2` marks a result carried from an earlier EdgeFirst Perception Index edition: this configuration was not re-measured on the current weights, so the row keeps the measurement, Studio session and model artifact of the edition that produced it. Rows without a badge come from the current edition.
 - **Precision** varies by target: the ONNX reference rows are FP32; macOS CoreML and NVIDIA Jetson TensorRT run FP16; the NXP i.MX 8M Plus, NXP i.MX 95 Neutron, and Hailo NPUs run INT8. The NXP Ara240 DNPU runs a **mixed INT8/INT16** scheme — most of the model is INT8, with the box-regression path (and the ops feeding it) promoted to INT16 to improve localization accuracy.
-- **Decoder variants.** EdgeFirst ships three INT8 split-decoders — **smart**, **logical**, and **combined** (described under *Decode* below). Every one we have measured is listed; none is headlined over another, because which one wins is a property of the target, not of the variant. Full converter documentation: [EdgeFirst model conversion](https://doc.edgefirst.ai/latest/models/conversion/) — these are the converters used by this Model Zoo and the EdgeFirst Performance Index report.
 - **Runtime.** Which inference stack executed the model. It is a column of its own because one accelerator can be reached by more than one: on Qualcomm Hexagon HTP, `ONNX · QNN EP` is an ONNX Runtime EPContext binary while `LiteRT` is the LiteRT + QNN delegate path, and the two produce measurably different pipelines from the same weights on the same silicon. Compare rows that share a size, platform, precision, and decode to read that difference directly.
 - **Decode.** What the exported graph emits, and therefore what your application has to do with it. **Logical** keeps the head's outputs separate and named — boxes, scores, and for segmentation the mask prototypes and coefficients — so reading them needs no decoder beyond taking the tensors as they come. **Smart** cuts the graph further upstream, at a point chosen by dynamic range and sliceability: the operations that quantize worst are lifted out of the model and run outside it, which is what recovers the accuracy, and which is why it needs a decoder implementing that cut (in EdgeFirst deployments, the HAL provides it). **Combined** fuses the decode into the quantized graph — the standard upstream export. It is the least accurate of the three by construction, and the EdgeFirst converters do not emit it for quantized targets; rows appear only where one was measured. Compare rows sharing a size and platform to see what the cut buys on your target — on detection it is often small, on quantized segmentation masks it is usually decisive. A `—` means the run carries no quantized decode split at all (float ONNX / TensorRT / CoreML).
 - **Rows are not ranked.** Where a size and platform appear more than once, the rows are competing configurations — a different runtime, precision, decode variant, pipeline mode, or board — not duplicates. Only genuinely repeated measurements of the *same* configuration are collapsed, newest first.

 - **Rows whose `Δ vs FP32` cell carries a ⚠** are below our accuracy expectations for that platform (more than 10 percentage points under the float reference). The numbers are real measurements on real hardware, reproducible from the linked Studio session, and we publish them as-is; we are investigating the results to make improvements, and the next snapshot of this card will reflect any recovered accuracy.
 - **Edition badges.** A Source cell such as `v-XXXX · 2026 Q2` marks a result carried from an earlier EdgeFirst Perception Index edition: this configuration was not re-measured on the current weights, so the row keeps the measurement, Studio session and model artifact of the edition that produced it. Rows without a badge come from the current edition.
 - **Precision** varies by target: the ONNX reference rows are FP32; macOS CoreML and NVIDIA Jetson TensorRT run FP16; the NXP i.MX 8M Plus, NXP i.MX 95 Neutron, and Hailo NPUs run INT8. The NXP Ara240 DNPU runs a **mixed INT8/INT16** scheme — most of the model is INT8, with the box-regression path (and the ops feeding it) promoted to INT16 to improve localization accuracy.
+- **Decoder variants.** EdgeFirst ships three INT8 split-decoders — **smart**, **logical**, and **combined** (described under *Decode* below). Every one we have measured is listed; none is headlined over another, because which one wins is a property of the target, not of the variant. Full converter documentation: [EdgeFirst model conversion](https://doc.edgefirst.ai/latest/models/conversion/) — these are the converters used by this Model Zoo and the EdgeFirst Perception Index report.
 - **Runtime.** Which inference stack executed the model. It is a column of its own because one accelerator can be reached by more than one: on Qualcomm Hexagon HTP, `ONNX · QNN EP` is an ONNX Runtime EPContext binary while `LiteRT` is the LiteRT + QNN delegate path, and the two produce measurably different pipelines from the same weights on the same silicon. Compare rows that share a size, platform, precision, and decode to read that difference directly.
 - **Decode.** What the exported graph emits, and therefore what your application has to do with it. **Logical** keeps the head's outputs separate and named — boxes, scores, and for segmentation the mask prototypes and coefficients — so reading them needs no decoder beyond taking the tensors as they come. **Smart** cuts the graph further upstream, at a point chosen by dynamic range and sliceability: the operations that quantize worst are lifted out of the model and run outside it, which is what recovers the accuracy, and which is why it needs a decoder implementing that cut (in EdgeFirst deployments, the HAL provides it). **Combined** fuses the decode into the quantized graph — the standard upstream export. It is the least accurate of the three by construction, and the EdgeFirst converters do not emit it for quantized targets; rows appear only where one was measured. Compare rows sharing a size and platform to see what the cut buys on your target — on detection it is often small, on quantized segmentation masks it is usually decisive. A `—` means the run carries no quantized decode split at all (float ONNX / TensorRT / CoreML).
 - **Rows are not ranked.** Where a size and platform appear more than once, the rows are competing configurations — a different runtime, precision, decode variant, pipeline mode, or board — not duplicates. Only genuinely repeated measurements of the *same* configuration are collapsed, newest first.