AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion

Junhao Su, Chenghao He, Feiyu Zhu, Xiaojie Xu, Dongzhi Guan, Chenyang Si

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 6 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 cascade local modules instead of independent local modules only (ablation)DGL, ResNet-32 K=16 · CIFAR-10test error (%): 14.08 -> 10.51Improved
combine independent and cascade levels (HiLo) (ablation)DGL, ResNet-32 K=16 · CIFAR-10test error (%): 10.51 -> 9.44Improved
add Patch Feature Fusion on top of HiLo (ablation)DGL, ResNet-32 K=16 · CIFAR-10test error (%): 9.44 -> 8.94Improved
add HiLo on InfoPro (ablation)InfoPro, ResNet-101 K=4 · ImageNetTop-1 error (%): 22.81 -> 21.35Improved
add Patch Feature Fusion on top of HiLo (ablation)InfoPro, ResNet-101 K=4 · ImageNetTop-1 error (%): 21.35 -> 21.14Improved
add Patch Feature Fusion to HiLo for memory (ablation)InfoPro, ResNet-32 K=16 · CIFAR-10GPU memory (GB): 3.13 -> 2.31Improved
add PFF to HiLo for accuracy (ablation)InfoPro, ResNet-32 K=16 · CIFAR-10test error (%): 9.59 -> 8.99Improved
apply HPFF to InfoPro on ImageNet ResNet-101 K=4InfoPro · ImageNetTop-1 error (%): 22.81 -> 21.14Improved
apply HPFF to DGL VGG13 K=10 on ImageNetDGL · ImageNetTop-1 error (%): 35.60 -> 32.49Mixed
apply HPFF to local learning on CIFAR-10DGL, InfoPro, PredSim · CIFAR-10 ResNet-110 K=55test error (%): 14.45 -> 8.74Mixed
apply HPFF to DGL, versus BP memoryDGL ResNet-110 K=55 · CIFAR-10GPU memory (GB): 9.26 -> 2.44Improved

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