AI Paper Atlas

Research map / Detection and segmentation / CNN features

TensorMask: A Foundation for Dense Object Segmentation

Xinlei Chen, Ross Girshick, Kaiming He, Piotr Dollar

ICCV 2019 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 429 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 aligned instead of natural representation with upscaling lambda=5 (ablation)TensorMask upscaling head · COCO valmask AP: 19.2 -> 28.4Improved
use aligned instead of natural representation with lambda=3 (ablation)TensorMask upscaling head · COCO valmask AP: 24.7 -> 28.8Improved
use aligned instead of natural representation with lambda=1.5 (ablation)TensorMask upscaling head · COCO valmask AP: 28.0 -> 28.9Improved
use aligned instead of natural representation without upscaling (ablation)TensorMask simple head · COCO valmask AP: 28.5 -> 28.9No clear effect
use bilinear instead of nearest-neighbor interpolation, lambda=5 (ablation)aligned upscaling head · COCO valmask AP: 25.3 -> 28.4Improved
use bilinear instead of nearest-neighbor interpolation, lambda=1.5 (ablation)aligned upscaling head · COCO valmask AP: 28.6 -> 28.9Improved
use tensor bipyramid instead of feature pyramid (ablation)TensorMask · COCO valmask AP: 28.9 -> 34.0Improved
use tensor bipyramid instead of feature pyramid (ablation)TensorMask · COCO valmask AP_L: 40.7 -> 48.4Improved
add a second window size 11x11 (ablation)TensorMask tensor bipyramid · COCO valmask AP: 34.0 -> 35.2Improved
add scale augmentation and longer 72-epoch scheduleMask R-CNN · COCO test-dev instance segmentationmask AP: 34.9 -> 36.8Improved
use TensorMask instead of Mask R-CNN (R-50)dense sliding-window segmentation · COCO test-dev instance segmentationmask AP: 36.8 -> 35.4Hurt
use TensorMask instead of Mask R-CNN (R-101)dense sliding-window segmentation · COCO test-dev instance segmentationmask AP: 38.3 -> 37.1Hurt

Later papers that compared with this method

14 later accepted papers report TensorMask as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.

6 more not listed.

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