AI Paper Atlas

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

FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous Driving

Xingtai Gui, Tengteng Huang, Haonan Shao, Haotian Yao, Chi Zhang

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 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
use multi-frame mask matching cost instead of single-frame mask cost in Hungarian matching (ablation)FipTR-T · nuScenes valVPQ(n): 51.1 -> 53.3Improved
add mask cost to the matching cost (ablation)FipTR-T · nuScenes valVPQ(n): 48.2 -> 53.3Improved
add the auxiliary 3D box branch to the instance mask decoder (ablation)FipTR-T · nuScenes valIoU / VPQ(n): 5.2 -> 59.0 IoU, 1.1 -> 33.6 VPQ (VPQ(f) column)Improved
add flow-aware deformable attention in place of vanilla deformable attention (ablation)FipTR-T · nuScenes valVPQ(n): 52.5 -> 53.3Improved
add FADA at far range (100m x 100m ROI) (ablation)FipTR-S · nuScenes valIoU(f): 40.4 -> 40.4No clear effect
replace RNN future BEV module with deformable attention based module (ablation)FipTR-T · nuScenes valVPQ(n): 46.7 -> 52.5Improved
use non-weight-shared Context CNN across future frames (ablation)FipTR-T · nuScenes valVPQ(n): 41.9 -> 53.3Improved
use non-weight-shared time-specific instance queries (ablation)FipTR-T · nuScenes valVPQ(n): 52.5 -> 53.3Improved
replace BEVerse with end-to-end FipTR on BEVDet4D encoder (Swin-S)BEVerse-S · nuScenes valVPQ(n): 51.7 -> 56.1Improved
replace UniAD with FipTR-R101 on BEVFormer encoderUniAD · nuScenes valIoU(n): 63.4 -> 62.9Mixed
replace PowerBEV with FipTR-T on IoU(n)PowerBEV · nuScenes valIoU(n): 62.5 -> 59.0Hurt
add segmentation (mask) branch alongside detection (ablation)FipTR-T · nuScenes valmAVE: 0.78 -> 0.51Improved

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