AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Advisable Learning for Self-Driving Vehicles by Internalizing Observation-to-Action Rules

Jinkyu Kim, Suhong Moon, Anna Rohrbach, Trevor Darrell, John Canny

CVPR 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Object-centric learning theory and video · 44 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add long-term (global) observation-action advice to discrete-command goal-conditioned modelgoal-conditioned driving model D · BDD-X control predictionADE median with speed inputs: 1.35 -> 0.81Improved
replace ConvNet from scratch with object-centric visual encoder (semantic segmentation + RoI pooling)model F · BDD-X control predictionADE median with speed inputs: 0.81 -> 0.65Improved
object-centric visual encodermodel F · BDD-X control predictionADE median without speed inputs: 2.14 -> 1.93Improved
add long-term advice to discrete-command modelmodel D · BDD-X control predictionADE median without speed inputs: 2.28 -> 2.14Mixed
object-centric visual encoder with semantic segmentation and RoI pooling, observation-to-action moduleobservation generation and action generation · BDD-X textual observation generationCIDEr-D: 70.1 -> 98.2 (vs best baseline)Improved
full advisable model with observation-to-action moduletextual action command generation · BDD-X textual action command generationCIDEr-D: 215.8 -> 338.5Improved
learned sim-based advice (red light, stop sign) given at test time in Carladriving model in Carla simulator · Carla stopping scenariosfailure rateImproved
add visual and textual explanations to the driving systemuser trust study · Carla human studyuser trust Likert (1-5): slight improvementImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy