computer vision

You can measure your heart rate with just a video of your face. No wearables, no fingertip sensors, just your webcam. I used remote photoplethysmography to track tiny color changes in the skin from blood flow. Got ~98% accuracy. Still blows my mind that a webcam can do this. [Video, 0:07, showing a pulse oximeter device clipped to a finger, displaying %SpO2 99 and PR bpm 70, next to a laptop keyboard/webcam setup — presumably ground-truth comparison for the video-based heart-rate measurement.]

Andi Marafioti (@andimarafioti), 10h: This is such a beautiful way to present ablations. Kind of jealous tbh [Embedded image — "Figure 2: Robust Image Pretraining" bar chart, table format] Columns: Robustness avg of 6 / ImageNet val | Training ZFLOPs 1. Baseline — 75.3 / 78.9 — 1.0 2. Prog. Res — 75.1 / 78.9 — 0.5 3. Batch Sz — 76.2 / 79.5 — 1.1 4. LAMB — 76.9 / 79.9 — 1.1 5. High Res — 78.3 / 80.4 — 1.2 6. RoPE — 79.2 / 80.7 — 1.2 7. Attn Pool — 80.1 / 81.0 — 1.2 8. Data Aug — 80.8 / 81.1 — 1.2 9. Mask Reg — 80.9 / 81.3 — 1.2 Figure caption: Figure 2 Robust Image Pretraining. We tune our pretraining recipe (§2.1) to maximize performance on a fixed set of data, starting with an OpenCLIP [49] ViT-L/14 model. We report cumulative zero-shot classification results for each modification. The inner bars show robustness evaluation, calculated as the average of 6 robustness benchmarks [4, 24, 44, 45, 109, 138], and the outer bars show ImageNet val [24] alone. Several changes significantly improve robustness, indicating that ImageNet val scales more with data, while robustness can scale with refined training techniques.