piatra . institutepathways
Explore/AI & computation/Begin with Fei-Fei Li

What does a vision benchmark leave outside its score?

A benchmark score evaluates a particular task and dataset, not every use of a deployed system.

AI & computationThinker · Selected readingBeginner friendly
Background and goal

No prior study required. Read the assigned passage; the route is an introduction, not a survey of the whole subject.

Design a small image-classification benchmark and list two deployment questions that accuracy alone would not answer.

Your pathway

4 steps · 3 hours
  1. 01

    Begin in fifteen minutes

    0.25h · week 1
    Reading notes and task
    First fifteen minutesWrite your initial answer to “What does a vision benchmark leave outside its score?” in three sentences. Keep it to compare with your final answer.
    Your outputThree-sentence starting answer
  2. 02

    Read the argument

    1h · week 1
    ImageNet: A Large-Scale Hierarchical Image Database

    Jia Deng · Wei Dong · Richard Socher · Li-Jia Li · Kai Li · Li Fei-Fei · paper

    Paper abstract, Introduction and Figure 1; leave technical evaluation details for deeper study.

    Free full text

    Open the reading
    Reading notes and task

    ImageNet: A Large-Scale Hierarchical Image Database. Computer vision and human-centred approaches to AI. Study the relationship among a dataset, a benchmark and the people affected by a system.

    Try thisRead Paper abstract, Introduction and Figure 1; leave technical evaluation details for deeper study.. Mark one claim, its reason and a passage you do not yet understand.
    Your outputAnnotated argument
    Check your understanding

    Answer this question in your own words: What does a vision benchmark leave outside its score?

    Hint

    Name the claim, then explain why a reader might accept it.

    Compare with an example answer

    A benchmark score evaluates a particular task and dataset, not every use of a deployed system.

    What to look for

    • States a claim that addresses the question
    • Connects the claim to a passage or observation
    • Separates the author’s argument from personal agreement

    Common mistake: Summarising a biography instead of explaining the argument.

    Start this pathway to keep your answers in My learning.

  3. 03

    Try the idea

    1h · week 1
    Reading notes and task
    Try thisDesign a small image-classification benchmark and list two deployment questions that accuracy alone would not answer.
    Your outputWorked example
    Check your understanding

    What would make your activity a convincing example?

    Hint

    Design a small image-classification benchmark and list two deployment questions that accuracy alone would not answer.

    Compare with an example answer

    A useful response carries out the task: Design a small image-classification benchmark and list two deployment questions that accuracy alone would not answer. It records the observation or passage used and explains how it bears on the question.

    What to look for

    • Completes the specific task
    • Shows evidence or reasoning rather than only a conclusion
    • Identifies an alternative explanation or reading

    Common mistake: Presenting an opinion without showing the example it rests on.

    Start this pathway to keep your answers in My learning.

  4. 04

    Explain what changed

    0.75h · week 1
    Reading notes and task
    Try thisRevise your initial answer. Include one passage, one reason and one limit: Keep a research result, an autobiographical account and a policy position distinct.
    Your outputRevised answer with a reading reference
    Check your understanding

    What is one conclusion this reading does not establish?

    Hint

    Test the boundary: Keep a research result, an autobiographical account and a policy position distinct.

    Compare with an example answer

    Keep a research result, an autobiographical account and a policy position distinct.

    What to look for

    • States a specific limit
    • Explains why the reading does not warrant the stronger conclusion
    • Distinguishes a limitation from dismissing the work

    Common mistake: Treating a useful interpretation as an unrestricted fact.

    Start this pathway to keep your answers in My learning.

All 1 resources

Background, different viewpoints, and further reading.

  • ImageNet: A Large-Scale Hierarchical Image Database

    Jia Deng · Wei Dong · Richard Socher · Li-Jia Li · Kai Li · Li Fei-Feipapercore

    Computer vision and human-centred approaches to AI. Study the relationship among a dataset, a benchmark and the people affected by a system.

    Paper abstract, Introduction and Figure 1; leave technical evaluation details for deeper study.

Continue learning

  • Study Fei-Fei Li

    Introduces the question and vocabulary used in the longer selected reading.

    AI & computationSome background