Opinion
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…”
Assertion Not checkable as stated
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.”
Assertion Partly supported
Robinson: 2024 DETR improvements are Pareto superior to YOLO
“And then how debtors are the improvements in 2024 to debtors that are making them a Pareto improvement to yellow base models.”
Assertion Supported
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.”
Assertion Supported
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…”
Assertion Supported
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.”
Assertion Supported
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…”
Assertion Supported
Robinson: High-Performance Diffusion Models Are Shifting to Rectified Flows
“It's also it's also worth noting that most diffusion models today, the very high performance ones are switching away from the classic like DDPM, Denoising Diffusion Probability Modeling Framework to rectified flows.”
Insight
Robinson: Rectified Flows Enable Faster Sampling by Approaching Single-Step Inference
“Rectified flows have a very interesting property of that. As they converge, they actually get closer to being able to be sampled with a single step, which means that in practice, you can actually generate high quality samples much faster.”
Assertion Not checkable as stated
Robinson: SAM has saved Roboflow users 75 years of labeling time
“SAM for us has saved our users 75 years of labeling time.”
Assertion Supported
Robinson: SAM 2's hierarchical encoder delivers 6x faster inference than ViT
“SAM replaced that with a hierarchical encoder, which gets approximately the same results, but leads to a six times faster inference, which is excellent, especially considering how in a trend of 23 was replacing the VIT with more efficient backbones.”
