AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency

Devendra Singh Chaplot, Murtaza Dalal, Saurabh Gupta, Jitendra Malik, Ruslan Salakhutdinov

NeurIPS 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Hand-object and articulated interaction · 10 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 random policy with Gainful Curiosity exploration policy (ablation)SEAL · Gibson test Generalizationobject detection AP50: 35.43 -> 40.02Improved
replace frontier exploration with Gainful Curiosity (ablation)SEAL · Gibson test Generalizationobject detection AP50: 37.39 -> 40.02Improved
replace Active Neural SLAM with Gainful Curiosity (ablation)SEAL · Gibson test Generalizationobject detection AP50: 38.90 -> 40.02Improved
replace Semantic Curiosity with Gainful Curiosity (ablation)SEAL · Gibson test Specializationobject detection AP50: 39.21 -> 41.23Improved
replace self-training with 3DLabelProp 3D-consistent labeling (ablation)SEAL · Gibson test Generalizationobject detection AP50: 35.35 -> 40.02Improved
replace optical flow label propagation with 3DLabelProp (ablation)SEAL · Gibson test Specializationobject detection AP50: 35.92 -> 41.23Improved
explore each test environment for one extra episode (Specialization)SEAL · Gibson testobject detection AP50: 40.02 -> 41.23Improved
swap pretrained Mask-RCNN for SEAL-improved perception in SemExpSemExp object goal navigation · Gibson Object Goal Navigationsuccess rate: 0.544 -> 0.627Improved
self-training or optical-flow baselines with other exploration policiesMask-RCNN · Gibson test Generalizationobject detection AP50: 34.82 -> 33.41 to 35.85No clear effect
fine-tune with k=10 human-labeled frames without label propagationMask-RCNN · Gibson testAP50No clear effect

Later papers that compared with this method

3 later accepted papers report Seal as a baseline in their results tables; 3 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