mlsanityData to 7 Oct 2026

7th AI Driving Olympics: 1st Place Report for Panoptic Tracking

arXiv 2112.05210 ↗First posted 9 Dec 2021cs.CV cs.LG cs.ROcited by 1

Not on the map. Why?

Abstract (arXiv)

In this technical report, we describe our EfficientLPT architecture that won the panoptic tracking challenge in the 7th AI Driving Olympics at NeurIPS 2021. Our architecture builds upon the top-down EfficientLPS panoptic segmentation approach. EfficientLPT consists of a shared backbone with a modified EfficientNet-B5 model comprising the proximity convolution module as the encoder followed by the range-aware FPN to aggregate semantically rich range-aware multi-scale features. Subsequently, we employ two task-specific heads, the scale-invariant semantic head and hybrid task cascade with feedback from the semantic head as the instance head. Further, we employ a novel panoptic fusion module to adaptively fuse logits from each of the heads to yield the panoptic tracking output. Our approach exploits three consecutive accumulated scans to predict locally consistent panoptic tracking IDs and also the overlap between the scans to predict globally consistent panoptic tracking IDs for a given sequence. The benchmarking results from the 7th AI Driving Olympics at NeurIPS 2021 show that our model is ranked #1 for the panoptic tracking task on the Panoptic nuScenes dataset.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 18 references that are in the map. First posted on arXiv 9 Dec 2021.

Builds on

15 of 18 references.

References · 15

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Mask R-CNNcited by 7,259
  3. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  4. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
  5. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  6. 2018Searching for Efficient Multi-Scale Architectures for Dense Image Predictioncited by 96
  7. 2021EfficientLPS: Efficient LiDAR Panoptic Segmentationcited by 76
  8. 2020MOPT: Multi-Object Panoptic Trackingcited by 53
  9. 2021Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Imagescited by 48
  10. 2021There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledgecited by 44
  11. 2021Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Soundscited by 40
  12. 2019Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learningcited by 37
3 more
  1. 2020Dynamic Object Removal and Spatio-Temporal RGB-D Inpainting via Geometry-Aware Adversarial Learningcited by 19
  2. 2021Unsupervised Domain Adaptation for LiDAR Panoptic Segmentationcited by 19
  3. 2018Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossingcited by 13

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 20234D-Former: Multimodal 4D Panoptic Segmentationcited by 12