Test photo breakfast-top-down

breakfast-top-down

License: CC0-1.0
Author: Andy Li
Source: Wikimedia Commons, https://commons.wikimedia.org/wiki/File:Breakfast_at_Coffee_1,_North_Street,_Taunton_2025-07-28.jpg (CC0 1.0 by the author, checked 2026-10-27); downscaled to 1600x1205, metadata removed
Hard cases: top-down, clutter, indoor

Hover any output to magnify the same spot in every output of that task.

Object detection

D-FINE l

D-FINE m

D-FINE n — D-FINE nFails: labels the cake slice as pizza

D-FINE s — D-FINE sFails: labels the cake slice as pizza

D-FINE x

DEIMv2 l

DEIMv2 m

DEIMv2 s

DEIMv2 x

Grounding DINO base

Grounding DINO tiny — Grounding DINO tinyFails: misses the table and the black coffee cup

GTR l

GTR m

GTR s

GTR x

LLMDet base — LLMDet baseFails: misses two of the three cups

LLMDet large

LLMDet tiny

MM-Grounding-DINO base — MM-Grounding-DINO baseFails: misses the black coffee cup

MM-Grounding-DINO large

MM-Grounding-DINO tiny — MM-Grounding-DINO tinyFails: misses two of the three cups

RF-DETR large

RF-DETR medium

RF-DETR nano

RF-DETR small

RT-DETRv4 l

RT-DETRv4 m

RT-DETRv4 s

RT-DETRv4 x

YOLO11 l

YOLO11 m

YOLO11 n — YOLO11 nFails: misses a latte cup, the fork and all the pastries

YOLO11 s

YOLO11 x

YOLO26 l

YOLO26 m

YOLO26 n

YOLO26 s

YOLO26 x

YOLOv8 l

YOLOv8 m

YOLOv8 n — YOLOv8 nFails: misses the black coffee, labels a latte cup as a bowl

YOLOv8 s

YOLOv8 x

Instance segmentation

EoMT large-1280

EoMT large-640

GTR-Seg l

GTR-Seg m

GTR-Seg s

GTR-Seg x

RF-DETR-Seg 2xlarge

RF-DETR-Seg large — RF-DETR-Seg largeFails: misses the leather chair at bottom left

RF-DETR-Seg medium — RF-DETR-Seg mediumFails: misses the black coffee cup

RF-DETR-Seg nano

RF-DETR-Seg small

RF-DETR-Seg xlarge

YOLO11-seg l

YOLO11-seg m

YOLO11-seg n — YOLO11-seg nFails: misses a cup, the fork and both knives, table mask on the floor

YOLO11-seg s

YOLO11-seg x

YOLO26-seg l — YOLO26-seg lFails: misses the leather chair at bottom left

YOLO26-seg m

YOLO26-seg n — YOLO26-seg nFails: misses the black coffee cup and the chair

YOLO26-seg s — YOLO26-seg sFails: misses the leather chair at bottom left

YOLO26-seg x

YOLOv8-seg l

YOLOv8-seg m

YOLOv8-seg n — YOLOv8-seg nFails: table mask spreads across the floor, cups masked as bowls

YOLOv8-seg s — YOLOv8-seg sFails: misses the big knife, table mask beside the table

YOLOv8-seg x