AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Textual Explanations for Self-Driving Vehicles

Jinkyu Kim, Anna Rohrbach, Trevor Darrell, John Canny, Zeynep Akata

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 392 citations (OpenAlex)

Read the paperCheck 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 visual attention to the CNN+FC controller (ablation)vehicle controller · BDD-X vehicle controlMAE acceleration (m/s^2): 6.92 -> 6.87Improved
add prior inputs (vehicle motion, navigation) to CNN+FC (ablation)CNN+FC controller · BDD-X vehicle controlMAE course (degree): 12.1 -> 6.74Improved
add prior inputs to CNN+LSTM+Attention (ablation)vehicle controller · BDD-X vehicle controlMAE acceleration (m/s^2): 6.87 -> 2.29Improved
increase entropy regularization lambda_c from 0 to 1000 (sparser attention) (ablation)vehicle controller · BDD-X vehicle controlMAE acceleration (m/s^2): 2.29 -> 5.02Hurt
increase entropy regularization lambda_c from 0 to 100 (ablation)vehicle controller · BDD-X vehicle controlMAE acceleration (m/s^2): 2.29 -> 2.68Hurt
add controller-explanation attention alignment (WAA) vs rationalization (ablation)explanation generator · BDD-X explanationsCIDEr-D: 61.99 -> 69.52Improved
add strongly aligned attention (SAA, lambda_c=100) vs rationalization (ablation)explanation generator · BDD-X explanationsCIDEr-D: 61.99 -> 66.09Improved
add entropy regularization lambda_c=100 to WAA (ablation)explanation generator · BDD-X explanationsCIDEr-D: 64.19 -> 69.52Improved
add weak alignment (WAA) instead of strong alignment (SAA), lambda_c=100 (ablation)explanation generator · BDD-X explanationsBLEU-4: 7.074 -> 7.281Improved
use controller inputs and attention in the justifier vs S2VT (ablation)explanation generator · BDD-X explanationsCIDEr-D: 53.35 -> 61.99Improved
add spatial attention to S2VT (ablation)S2VT · BDD-X explanationsCIDEr-D: 53.35 -> 51.37Hurt
add spatial and temporal attention to S2VT (ablation)S2VT · BDD-X explanationsCIDEr-D: 53.35 -> 52.74No clear effect

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