AI Paper Atlas

Research map / Detection and segmentation / CNN features

End-to-End Egospheric Spatial Memory

Daniel James Lenton, Stephen James, Ronald Clark, Andrew Davison

ICLR 2021 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 3 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 ESM instead of the PO2 baselineDrone Reacher, Ego Acq, Shape · Drone Reacher, Ego Acq, Shapetargets reached: 14.4(6.1) -> 18.3(6.4)Improved
use ESM instead of the PO2 baselineDrone Reacher, Freeform Acq, Color · Drone Reacher, Freeform Acq, Colortargets reached: 19.1(12.7) -> 16.6(12.9)Hurt
use ESM instead of the PO2 baselineManipulator Reacher, Ego Acq, Color · Manipulator Reacher, Ego Acq, Colortargets reached: 13.0(5.9) -> 11.7(5.3)Hurt
use ESM instead of the PO2 baselineManipulator Reacher, Freeform Acq, Color · Manipulator Reacher, Freeform Acq, Colortargets reached: 12.5(6.1) -> 11.0(5.8)Hurt
learn encoded features before storing them in ESM rather than directly projecting RGB (ablation)ESMN · Drone Reacher, Ego Acq, Shapetargets reached: 4.1(3.8) -> 18.3(6.4)Improved
learn encoded features before storing them in ESM rather than directly projecting RGB (ablation)ESMN · ScanNet test, 60×80 images, 90×180 memory, 16-framesegmentation accuracy: 54.1(13.8) -> 59.4(12.7)Improved
use an ESM depth map instead of a single depth frame for avoidanceESMN-RGB policy · Obstacle avoidancecollisions: 10.8(13.0) -> 2.7(5.5)Improved
add untuned spatial auxiliary losses to the LSTM (ablation)LSTM-Aux · Reacher taskstargets reachedHurt
transfer an ESMN policy across camera modalities without further trainingESMN · Reacher camera transfertargets reached: 20.8(7.8) -> 10.4(5.5); 18.3(6.4) -> 0.7(0.9); 16.6(12.9) -> 8.9(6.5); 8.5(11.2) -> 1.0(1.4); 11.7(5.3) -> 7.5(4.9); 4.7Mixed
train an ESM policy with reinforcement learning rather than imitation learningESMN and ESMN-RGB · MR-Seq-Ego-Colortargets reachedImproved

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