AI Paper Atlas

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

TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving

Kashyap Chitta, Aditya Prakash, Bernhard Jaeger, Zehao Yu, Katrin Renz, Andreas Geiger

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 616 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 transformer-based global fusion instead of geometry-based fusionTransFuser · Longest6Driving Score: 27.32 -> 47.30Improved
add transformer-based fusion instead of late fusionTransFuser · Longest6Driving Score: 22.47 -> 47.30Improved
add LiDAR fusion via transformers on top of image-only Latent TransFuserTransFuser · CARLA leaderboardDriving Score: 45.20 -> 61.18Improved
add all four auxiliary losses (ablation)TransFuser · Longest6Route Completion: 78.17 -> 92.28Improved
add all four auxiliary losses (ablation)TransFuser · Longest6Driving Score: 44.29 -> 56.68Improved
add depth loss alone (ablation)TransFuser · Longest6Driving Score: 56.23 vs 56.68 best seedNo clear effect
add global safety heuristic (also during regular driving)Latent TransFuser · Longest6Driving Score: 42.19 -> 50.00Improved
add global safety heuristic (also during regular driving)TransFuser · CARLA leaderboardDriving Score: 50.57 -> 41.93Hurt
add global safety heuristic (also during regular driving)TransFuser · Longest6Driving Score: 42.51 -> 49.49Improved
ensemble 3 modelsTransFuser · CARLA leaderboardDriving Score: 50.57 -> 61.18Improved
ensemble 3 modelsLatent TransFuser · Longest6Driving Score: 42.19 -> 36.18Hurt
use 4 fusion scales instead of only deepest 1, 2 or 3 (ablation)TransFuser · Longest6Driving Score: 49.35, 53.52, 48.77 for 1, 2, 3 scales vs 56.68Improved

Later papers that compared with this method

16 later accepted papers report TransFuser as a baseline in their results tables; 15 of them report a better number on most of the results they share with it.

8 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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