Robinson: 2024 DETR improvements are Pareto superior to YOLO
Isaac Robinson · Best of 2024 in Vision [LS Live @ NeurIPS] · Dec 22, 2024 · at 1:28
Isaac Robinson of Roboflow discusses technical advances in object detection models at NeurIPS 2024.
0:00 / 0:08exact quote · 8.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“And then how debtors are the improvements in 2024 to debtors that are making them a Pareto improvement to yellow base models.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Isaac Robinson
Robinson: YOLO architectures have hit a performance plateau
“So, for years, yellows have been the dominant way of doing real time object detection, and we can see here that they've essentially stagnated. The performance between 10 and 11 is not meaningfully different. At least, you know, in, in this type of high level c…”
Robinson: DETRs are replacing YOLO in real-time object detection
“And then also how debtors are starting to take over the real time object detection scene from YOLOs which have been dominant for years.”
Robinson: Factoring in NMS Latency Shows DETRs Outperform YOLO
“Once you include the NMS in the latency calculation, you see that, in fact, these debtors are outperforming, at least at this time, the yellows that existed.”
Robinson: Original DiT Research Showed Compute Scaling Outweighed Hyperparameters
“This is so interesting because the original diffusion transformer paper from Facebook actually showed that, in fact, the specific hyperparameters of the transformer didn't really matter that much. What mattered was that you were just increasing the amount of c…”
Robinson: D-FINE models achieve +4.6 AP over YOLO at equivalent latency
“So, we can look here and see the yellow series has this plateau and then these RT debtor, LW debtor and define have meaningfully changed that plateau so that in fact the best defined models are plus 4.6 AP on Coco at the same latency.”
Robinson: YOLO and real-time detectors historically gained little from pre-training
“And the other thing is, until recently, the real time object detectors didn't even really benefit from pre-training. Like, you see the Yolos that are, like, essentially saturated showing very little difference with pretraining improvements with using pretraine…”