AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

Abhinav Kumar, Garrick Brazil, Enrique Corona, Armin Parchami, Xiaoming Liu

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 90 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 vanilla convolutions with scale-equivariant SES convolutionsGUP Net · KITTI Val carsAP3D|R40 Moderate (%): 15.48 -> 16.54Improved
add scale equivariance on top of scale augmentation (ablation)GUP Net · KITTI Val carsAP3D|R40 Easy (%): 21.10 -> 24.63Improved
use SES convolution instead of log-polar convolution (ablation)DEVIANT · KITTI Val carsAP3D|R40 Moderate (%): 6.77 -> 16.54Improved
use SES convolution instead of dilated convolution (ablation)DEVIANT · KITTI Val carsAP3D|R40 Moderate (%): 15.49 -> 16.54Improved
use SES convolution instead of DISCO (ablation)DEVIANT · KITTI Val carsAP3D|R40 Moderate (%): 13.84 -> 16.54Improved
use floating downscaling alpha 10% instead of 5% (ablation)DEVIANT · KITTI Val carsAP3D|R40 Moderate (%): 16.51 -> 16.54Improved
use floating downscaling alpha 10% instead of 20% (ablation)DEVIANT · KITTI Val carsAP3D|R40 Moderate (%): 15.85 -> 16.54Improved
make batch norm and pooling scale-equivariant too (ablation)DEVIANT · KITTI Val carsAP3D|R40 Moderate (%): 16.20 -> 16.54Improved
use three Hermite scales instead of one (ablation)DEVIANT · KITTI Val carsAP3D|R40 Hard (%): 13.63 -> 14.52Improved
use three Hermite scales instead of two (ablation)DEVIANT · KITTI Val carsAP3D|R40 Moderate (%): 16.48 -> 16.54Improved
replace scale-equivariant backbone with DETR3D transformerDEVIANT · KITTI Val carsAP3D|R40 Moderate (%): 1.26 -> 16.54Improved
use DEVIANT backbone instead of vanillaGUP Net · KITTI Val to nuScenes frontal Valdepth MAE (all): 1.45 -> 1.26Improved

Later papers that compared with this method

7 later accepted papers report DEVIANT as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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