cellcanvas / cellcanvas/cellcanvas-prototype

feature: suggesting regions to label that are "hard to predict"

Open
#41 0 comments 1 reaction 0 assignees View on GitHub
Dominant language
Python
Stars
12
Forks
5
PR merge metrics
No merged PRs in 30d

Description

we can look into suggesting regions that are hard to predict by looking at where the prediction differs from the labels. We can then find similar pixels based on embeddings and suggest the user paint those regions.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by tracing where predictions, labels, and pixel embeddings are produced and compared. Done means the tool identifies regions where predictions differ from labels, finds similar pixels using embeddings, and suggests regions for the user to paint.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.