AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Self-Born Wiring for Neural Trees

Ying Chen, Feng Mao, Jie Song, Xinchao Wang, Huiqiong Wang, Mingli Song

ICCV 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Tree ensemble optimization · 7 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 self-born wiring instead of random wiring (ablation)SeBoW-A · CIFAR-10accuracy (%): 83.32 -> 93.45 (same 1.0M params)Improved
use self-born wiring instead of random wiring (ablation)SeBoW-C · CIFAR-100accuracy (%): 67.04 -> 74.59Improved
use self-born wiring instead of random wiring (ablation)SeBoW-B · CIFAR-100accuracy (%): 63.42 -> 71.79Improved
use self-born wiring instead of random wiring (ablation)SeBoW-B · CIFAR-10accuracy (%): 84.04 -> 94.00Improved
add senders (ablation)SeBoW-B · CIFAR-100accuracy (%): 52.89 -> 71.79Improved
add senders (ablation)SeBoW-C · ImageNettop-1 accuracy (%): 62.29 -> 70.13Improved
add senders (ablation)SeBoW-C · tiny-ImageNetaccuracy (%): 42.01 -> 58.77Improved
add receivers (ablation)SeBoW-A · CIFAR-10accuracy (%): 92.55 -> 93.45Improved
add receivers (ablation)SeBoW-C · tiny-ImageNetaccuracy (%): 54.42 -> 58.77Improved
add receivers (ablation)SeBoW-C · CIFAR-100accuracy (%): 74.59 -> 74.59No clear effect
use single-path instead of multi-path inferenceSeBoW-C · ImageNettop-1 accuracy (%): 70.13 -> 69.86; params 16.90M -> 14.78MHurt
increase base learner width from SeBoW-A to SeBoW-CSeBoW · CIFAR-10accuracy (%): 93.45 -> 94.33Improved

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