mlsanityData to 7 Oct 2026

A Vanilla Multi-Task Framework for Dense Visual Prediction Solution to 1st VCL Challenge -- Multi-Task Robustness Track

arXiv 2402.17319 ↗First posted 27 Feb 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this report, we present our solution to the multi-task robustness track of the 1st Visual Continual Learning (VCL) Challenge at ICCV 2023 Workshop. We propose a vanilla framework named UniNet that seamlessly combines various visual perception algorithms into a multi-task model. Specifically, we choose DETR3D, Mask2Former, and BinsFormer for 3D object detection, instance segmentation, and depth estimation tasks, respectively. The final submission is a single model with InternImage-L backbone, and achieves a 49.6 overall score (29.5 Det mAP, 80.3 mTPS, 46.4 Seg mAP, and 7.93 silog) on SHIFT validation set. Besides, we provide some interesting observations in our experiments which may facilitate the development of multi-task learning in dense visual prediction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 23 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

21 of 23 references.

References · 21

  1. 2017Mask R-CNNcited by 7,259
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  4. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  5. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  6. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  7. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  8. 2019PointRend: Image Segmentation as Renderingcited by 439
  9. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  10. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  11. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  12. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
9 more
  1. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  2. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  3. 2023Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 82
  4. 2022BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detectioncited by 66
  5. 2023Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perceptioncited by 65
  6. 2022DETRDistill: A Universal Knowledge Distillation Framework for DETR-familiescited by 36
  7. 2022Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detectioncited by 35
  8. 2022Deliberated Domain Bridging for Domain Adaptive Semantic Segmentationcited by 31
  9. 20201st Place Solutions of Waymo Open Dataset Challenge 2020 -- 2D Object Detection Trackcited by 5

Built on by

Not cited yet.