AI Paper Atlas

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

Deep Texture Manifold for Ground Terrain Recognition

Jia Xue, Hang Zhang, Kristin Dana

CVPR 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 150 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
Combine orderless texture encoding with global-average-pooled spatial information using a bilinear modelResNet-18 · GTOS-mobile, single scaleaccuracy: 74.22 -> 76.07Improved
Combine orderless texture encoding with global-average-pooled spatial information using a bilinear modelResNet-18 · GTOS-mobile, multi scaleaccuracy: 76.12 -> 82.18Improved
Use multi-scale rather than single-scale trainingDEP · GTOS-mobileaccuracy: 76.07 -> 82.18Improved
Use multi-scale rather than single-scale trainingResNet · GTOS-mobileaccuracy: 70.82 -> 73.16Improved
Use multi-scale rather than single-scale trainingBilinear CNN · GTOS-mobileaccuracy: 72.03 -> 75.43Improved
Use multi-scale rather than single-scale trainingDeep-TEN · GTOS-mobileaccuracy: 74.22 -> 76.12Improved
Combine texture and spatial features in DEP instead of using global-average-pooled spatial features aloneResNet-18 · GTOS-mobile, multi scaleaccuracy: 73.16 -> 82.18; 9.02%Improved
Combine texture and spatial features in DEP instead of texture details aloneDeep-TEN · GTOS-mobile, multi scaleaccuracy: 76.12 -> 82.18; 6%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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