AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

Liang Liu, Hao Lu, Hongwei Zou, Haipeng Xiong, Zhiguo Cao, Chunhua Shen

ECCV 2020 · Reinforcement learning › MDPs and planning · approach: POMDPs and confounded RL · 91 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 guiding reward (ablation)LibraNet · ShanghaiTech Part AMAE: 149.8 -> 55.9Improved
add force ending reward (ablation)LibraNet · ShanghaiTech Part AMAE: 62.7 -> 55.9Improved
add squeezing reward (ablation)LibraNet · ShanghaiTech Part AMAE: 63.5 -> 55.9Improved
Q-learning with designed rewards instead of imitation of optimal actions (ablation)LibraNet · ShanghaiTech Part AMAE: 64.7 -> 55.9Improved
increase maximum step from 4 to 8 (ablation)LibraNet · ShanghaiTech Part AMAE: 126.3 -> 55.9Improved
increase maximum step from 8 to 12 (ablation)LibraNet · ShanghaiTech Part AMAE: 55.9 -> 62.5Hurt
tolerance range 0.5 versus 0.1 (ablation)LibraNet · ShanghaiTech Part AMAE: 61.0 -> 55.9Improved
add LibraNet to ImageNet-pretrained classification baseline (ablation)ImageNet Classification · ShanghaiTech Part A (plug-in)MAE: 140.4 -> 119.7Improved
add LibraNet to ImageNet-pretrained regression baseline (ablation)ImageNet Regression · ShanghaiTech Part A (plug-in)MAE: 156.2 -> 126.6Improved
add LibraNet to TasselNetv2 (ablation)TasselNetv2 · ShanghaiTech Part A (plug-in)MAE: 68.6 -> 64.7Improved
add LibraNet to blockwise classification (ablation)Blockwise Classification · ShanghaiTech Part A (plug-in)MAE: 62.8 -> 55.9Improved
sequential decision (LibraNet) versus BCNet on patch-level countingBCNet · ShanghaiTech Part AGAME3: 116.7 -> 113.1Improved

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