Learn the paper. Keep the understanding. Margin is an early experiment. Work through one paper, try its ideas, and see what you can use the next day. First up: Focal Loss.

Start the lesson →
Margin
ONE PAPER · READER PREVIEW
Sign in with Google

A guided reading of one paper

Focal Loss for Dense Object Detection.

Why would a model need to spend less effort on examples it already gets right? Work through the idea, try it yourself, and check each step against the paper.

Browse the complete paper 10 pages · original PDF
ORIGINAL PAPERFigure 1 · loss curves
Original PDF ↗
100%

Loading the original PDF…

If the source cannot load, open the original page ↗.

YOUR READING GUIDE

We’ll follow one idea: changing how much each training example contributes to the loss. Start with the problem, explore the equation, then see what the authors tested. The full paper is here whenever you need it.

Your notes stay on this device. Privacy details

Intro · start with the problem

01 / THE INTRODUCTION

Why easy examples can get in the way.

Imagine teaching a model to find objects in a photo. It checks many locations and asks: “Is there an object here?” Most locations are background.

Training uses a loss to measure how far each prediction is from the known answer. Once the model gets a background example right with high confidence, that example adds only a small loss. A huge number of small losses can still add up.

Pause here. If most of the total loss comes from examples the model already gets right, what might happen to the examples it still struggles with?

What would you like to get out of this?

Source: the authors' problem statement in the abstract and introduction, pp. 1–2.