AI Paper Atlas

Research map / Detection and segmentation / CNN features

AutoBSS: An Efficient Algorithm for Block Stacking Style Search

Yikang Zhang, Jian Zhang, Zhao Zhong

NeurIPS 2020 · Detection and segmentation › CNN features · approach: Efficient network training and design · 0 citations (OpenAlex)

Read the paper

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
search BSS with AutoBSSResNet18 · ImageNettop-1 accuracy (350 ep): 72.19 -> 73.91Improved
search BSS with AutoBSSResNet50 · ImageNettop-1 accuracy (350 ep): 77.69 -> 79.29Improved
search BSS with AutoBSSMobileNetV2 · ImageNettop-1 accuracy (350 ep): 73.90 -> 74.50Improved
search BSS with AutoBSSEfficientNet-B0 · ImageNettop-1 accuracy: 77.12 -> 77.79Improved
search BSS with AutoBSSEfficientNet-B1 · ImageNettop-1 accuracy: 79.19 -> 79.48Improved
use AutoBSS instead of random search of 64 BSSCResNet18 · ImageNettop-1 accuracy (120 ep): 72.34 -> 73.22Improved
use AutoBSS instead of random search of 64 BSSCResNet50 · ImageNettop-1 accuracy (120 ep): 77.48 -> 78.17Improved
use AutoBSS instead of random search of 64 BSSCMobileNetV2 · ImageNettop-1 accuracy (120 ep): 72.13 -> 72.96Improved
use AutoBSS instead of random search of 64 BSSCEfficientNet-B0 · ImageNettop-1 accuracy: 76.73 -> 77.79Improved
add BSS Clustering to the search (ablation)AutoBSS on ResNet18 · ImageNetmean top-1 of best 5 BSS: 72.62 -> 73.08Improved
use AutoBSS instead of uniform rescaling or pruning for compressionMobileNetV2 at 130M FLOPs · ImageNettop-1 accuracy: 68.05 -> 69.65Improved
search BSS with AutoBSSMask R-CNN-R50 · COCOAP bbox: 39.24 -> 40.15Improved

Earlier methods this paper compares with

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