AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL

Fangwei Zhong, Kui Wu, Hai Ci, Chu-ran Wang, Hao Chen

ECCV 2024 · Reinforcement learning › Visual and representation RL · approach: Robust visual encoders for RL · 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
add text-conditioned segmentation masks from a VFM as the state instead of raw RGB (ablation)Offline RL tracker · Complex Roomsuccess rate: 0.03 -> 0.92Improved
add re-targeting mechanism (target shown in white) (ablation)Ours (DEVA) · Complex Roomsuccess rate: 0.57 -> 0.92Improved
add recurrent (LSTM) temporal encoder (ablation)Ours (DEVA) · Complex Roomsuccess rate: 0.60 -> 0.92Improved
use DEVA with text prompt rather than DINOv2 masks (ablation)Offline RL tracker · Complex Roomsuccess rate: 0.74 -> 0.92Improved
swap DEVA for SAM-Track as the VFM (ablation)Ours · Complex Roomsuccess rate: 0.92 -> 0.97Improved
use moderate action noise (level 2) in data collection rather than level 1 or 4 (ablation)Ours · Complex Room (40k)success rate: 0.18 (level 1), 0.82 (level 2), 0.45 (level 4)Mixed
increase offline dataset from 20k to 80k steps (ablation)Ours · Complex Roomsuccess rate: 0.23 (20k), 0.82 (40k), 0.76 (80k)Mixed
scale BC expert data from 200k to 1000k steps (ablation)Behavior Cloning · Complex Roomsuccess rate: 0.32 -> 0.49No clear effect
offline RL with multi-level noisy data instead of BC on expert dataEmbodied visual tracker · Mean over 5 unseen environmentssuccess rate: 0.32 -> 0.95Improved
train offline for 1 hour instead of online RL for 12-26 hoursEmbodied visual tracker · Mean over 5 unseen environmentssuccess rate: 0.95 vs 0.92 (RSPT), 0.86 (TS)Mixed
add RNN for distractor robustness on unseen animal targets (ablation)Ours · Animals (4D), Simple Roomsuccess rate: 0.77 -> 0.84Improved

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