How an object detector turns 1,917 guesses into a few boxes
Run a real detector on a photo or your webcam, then tune the thresholds that turn 1,917 guesses into a few boxes.
Essays, notebooks, and field notes connected by computer vision.
Run a real detector on a photo or your webcam, then tune the thresholds that turn 1,917 guesses into a few boxes.
Type any labels and let CLIP pick one for a photo, then search images with plain text.
Use matched seeds and original diffusion trajectories to separate conditioning, scheduler choices and evaluation claims.
Transfer learning with a frozen MobileNet embedding and a k-nearest-neighbor head, and where the trick breaks down.
Spatial grounding depends on preserving coordinates, local visual tokens, and training the decoder to speak in regions.
How an image becomes a sequence of patches, and why attention changed the computer-vision toolbox.
Phi-3.5 Vision and Florence-2 look similar at the input, but they are built for rather different jobs.