Suspect choice for the paper to only include a single DETR from 2022 in the headline pareto chart and claim to have "the strongest AP–latency trade-off"... Clearly the authors were aware of models that exceed theirs given they even mentioned some of them in the introduction.
> In parallel, DETR [5] cast detection as end-to-end set prediction, and its real-time descendants (RT-DETR [98], D-FINE [55], DEIM [21], RF-DETR [62]) have narrowed the accuracy gap with CNN based detectors on standard benchmarks.
dheera | 18 hours ago
andwaal | 17 hours ago
robotresearcher | 17 hours ago
mnky9800n | 16 hours ago
speed_spread | 12 hours ago
vergessenmir | 16 hours ago
steinvakt2 | 13 hours ago
JohnKemeny | 13 hours ago
77 points, 24 comments
https://news.ycombinator.com/item?id=48639165
yeldarb | 11 hours ago
> In parallel, DETR [5] cast detection as end-to-end set prediction, and its real-time descendants (RT-DETR [98], D-FINE [55], DEIM [21], RF-DETR [62]) have narrowed the accuracy gap with CNN based detectors on standard benchmarks.