AI Paper Atlas

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

CarFormer: Self-Driving with Learned Object-Centric Representations

Shadi Hamdan, Fatma Guney

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Slot attention methods · 8 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
replace exact object attributes with learned slot representationsCarFormer · Longest6Driving Score: 71.53 -> 74.89Improved
use object-level slots instead of scene-level VQ-VAE BEV tokensCarFormer · Longest6Driving Score: 17.07 -> 74.89Improved
predict waypoints with GRU head instead of quantized transformer head (ablation)CarFormer (slots) · Longest6Driving Score: 66.87 -> 74.89Improved
add block attention (ablation)CarFormer (slots) · Longest6Driving Score: 70.42 -> 74.89Improved
add auxiliary slot forecasting (ablation)CarFormer (slots) · Longest6Driving Score: 57.25 -> 74.89Improved
add creeping during evaluation (ablation)CarFormer (slots) · Longest6Driving Score: 69.16 -> 74.89Improved
remove creeping (infraction score) (ablation)CarFormer (slots) · Longest6Infraction Score: 0.79 -> 0.83Improved
increase number of slots from 7 to 30 (ablation)CarFormer (slots, not enlarged) · Longest6Driving Score: 48.17 -> 71.48Improved
enlarge small vehicles in BEV for slot extraction (ablation)CarFormer (slots, 7 slots) · Longest6Driving Score: 48.17 -> 62.93Improved
enlarge small vehicles in BEV for slot extraction (ablation)CarFormer (slots, 30 slots) · Longest6Driving Score: 71.48 -> 74.89Improved
CarFormer with exact attributes vs PlanT architectureCarFormer (attributes) · Longest6Driving Score: 73.36 -> 71.53No 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