AI Paper Atlas

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

Search for or Navigate to? Dual Adaptive Thinking for Object Navigation

Ronghao Dang, Liuyi Wang, Zongtao He, Shuai Su, Jiagui Tang, Chengju Liu, Qijun Chen

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Hand-object and articulated interaction · 33 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
add search thinking (object association via DOA) (ablation)end-to-end baseline · AI2-Thor ALLSR: 71.34 -> 74.89Improved
add imitation-learning pretraining of search thinking network (ablation)search thinking · AI2-Thor ALLSR: 74.89 -> 75.90Improved
add TOMG navigation memory without TAMSA (ablation)search thinking model · AI2-Thor ALLSPL: 45.04 -> 43.15 (SPL); 121.53 -> 126.15 (SNE)Mixed
add TAMSA after TOMG and egocentric transform (ablation)navigation thinking · AI2-Thor ALLSPL: 42.01 -> 45.71Improved
add egocentric coordinate transformation (with TAMSA) (ablation)navigation thinking · AI2-Thor ALLSR: 78.04 -> 80.88Improved
add adaptive fusion (ablation)DAT · AI2-Thor ALLSPL: 45.71 -> 47.53Improved
add layer normalization after concatenating the two thinking features (ablation)DAT fusion · AI2-Thor ALLSR: 81.34 -> 82.39Improved
use TAMSA instead of Transformer or TCN encoder (ablation)navigation thinking · AI2-Thor ALLSR: 77.23 -> 82.39 (vs Transformer)Improved
use TCN or transformer instead of plain average pooling (ablation)navigation thinking aggregator · AI2-Thor ALLSR: 79.67 -> 77.23 (transformer)Hurt
add target-aware property to TAMSA dynamic aggregator (ablation)TAMSA · AI2-Thor ALLSR: 80.15 -> 81.20Improved
add multi-scale kernels to TAMSA (ablation)TAMSA · AI2-Thor ALLSPL: 44.26 -> 47.28Improved
add circle padding (ablation)TAMSA · AI2-Thor ALLSR: 81.32 -> 82.39Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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