AI Paper Atlas

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

VTNet: Visual Transformer Network for Object Goal Navigation

Heming Du, Xin Yu, Liang Zheng

ICLR 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Hand-object and articulated interaction · 36 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 VTNet instead of BaselineAI2-Thor navigation · AI2-Thor test, ALLSuccess: 62.6 -> 72.2Improved
use VTNet instead of ORG+TPNAI2-Thor navigation · AI2-Thor test, ALLSuccess: 69.3 -> 72.2Improved
add global features (ablation)VTNet · AI2-Thor test, ALLSuccess: 67.0 -> 72.2Improved
add the VT decoder to attend global descriptors to local descriptors (ablation)VTNet · AI2-Thor test, ALLSuccess: 67.0 -> 72.2Improved
add positional embedding to global features (ablation)VTNet · AI2-Thor test, ALLSuccess: 71.0 -> 72.2Improved
use VTNet's decoder arrangement instead of feeding positional global features into the encoder (ablation)VTNet · AI2-Thor test, ALLSuccess: 70.1 -> 72.2Improved
use DETR instance features instead of Faster R-CNN features (ablation)VTNet · AI2-Thor test, ALLSuccess: 70.1 -> 72.2Improved
use DETR instance features instead of Faster R-CNN† features (ablation)VTNet · AI2-Thor test, ALLSuccess: 70.3 -> 72.2Improved
pre-train VT with optimal action instructions (ablation)VTNet · AI2-Thor navigationnavigation policy effectivenessImproved
use 2 encoder and 2 decoder layers instead of 1 each (ablation)VTNet · AI2-Thor testSuccess: 71.2 -> 72.2Improved
use 2 encoder and 2 decoder layers instead of 4 each (ablation)VTNet · AI2-Thor testSuccess: 70.0 -> 72.2Improved
use 4 attention heads instead of 8, with 2 encoder and decoder layers (ablation)VTNet · AI2-Thor testSuccess: 70.9 -> 72.2Improved

Later papers that compared with this method

1 later accepted paper reports VTNet as a baseline in their results tables; 1 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