AI Paper Atlas

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

Learning Gabor Texture Features for Fine-Grained Recognition

Lanyun Zhu, Tianrun Chen, Jianxiong Yin, Simon See, Jun Liu

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 77 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 Gabor texture branch and region selection gate (ablation)ResNet50 · CUB-200-2011accuracy (%): 84.5 -> 90.8Improved
add region selection gate to texture branch (ablation)texture branch · CUB-200-2011accuracy (%) and FLOPs: 89.0 -> 90.8; 36.88G -> 20.72G FLOPsImproved
use Gabor filters instead of 3x3 convolutions (ablation)texture branch · CUB-200-2011accuracy (%): 85.9 -> 90.8Improved
learn Gabor parameters in supervised manner instead of manual setting (ablation)Gabor filters · CUB-200-2011accuracy (%): 86.5 -> 90.8Improved
add parameter value constraints to learnable Gabor filters (ablation)Gabor filters · CUB-200-2011accuracy (%): 75.4 -> 90.8Improved
add high frequency enhancement strategy (ablation)Gabor filters · CUB-200-2011accuracy (%): 88.1 -> 90.8Improved
add Learnable Histogram Operator (ablation)statistical feature extractor · CUB-200-2011accuracy (%): 87.0 -> 90.8Improved
add Filter Correlation Module (ablation)statistical feature extractor · CUB-200-2011accuracy (%): 89.2 -> 90.8Improved
use LHO instead of hand-crafted statistics (ablation)texture branch · CUB-200-2011accuracy (%): 87.9 -> 90.8Improved
place LHO on Gabor texture branch rather than CNN branch (ablation)LHO · CUB-200-2011accuracy (%): 86.2 -> 90.8Improved
apply method to ImageNet instead of fine-grained dataResNet50 · ImageNettop-1 accuracy (%): 76.1 -> 77.9Improved
vary loss weight lambda from 0.01 to 1 (ablation)full method · CUB-200-2011accuracy (%): 90.0 to 90.8No clear effect

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