List your company

Fine-grained Image Classification on NABirds

91.45AccuracyTRD
-3.29421.30345.970.497Sep 10, 2019May 17, 2020Jan 23, 2021Oct 1, 2021Jun 9, 2022Feb 15, 2023Oct 24, 2023

Evaluation results

MethodLinks
TRD2023.1091.45—
Relational Proxies2023.1091.2—
CAPTraining data setup=primary2021.0191—
CAP2023.1091—
TransFG2023.1090.8—
FFVT2023.1089.42—
GaRD2023.1088—
DSTLTraining data setup=primary + secondary2021.0187.9—
MMAL2023.1087.1—
Cross-XTraining data setup=primary2021.0186.4—
MaxEntTraining data setup=primary + secondary2021.0183—
PC-CNNTraining data setup=primary2021.0182.8—
T-LossTraining data setup=primary2021.0179.6—
StochNorm2023.1074.94—
Cross X (SENet)Backbone=SENet-50, 1-Stage=true, Sep. Init.=false2019.090.864—
Cross X (ResNet)Backbone=ResNet-50, 1-Stage=true, Sep. Init.=false2019.090.862—
MaxEnt-CNNBackbone=DenseNet-161, 1-Stage=true, Sep. Init.=false2019.090.83—
ResNet-501-Stage=true, Sep. Init.=false2019.090.822—
SENet-501-Stage=true, Sep. Init.=false2019.090.821—
PN-CNN1-Stage=false, Sep. Init.=true2019.090.74—
MaxEnt-CNNBackbone=ResNet-50, 1-Stage=true, Sep. Init.=false2019.090.692—
AlexNet-fc61-Stage=false, Sep. Init.=true2019.090.35—
BIOCAPZero-shot=true, Visual Encoder=ViT-B/162025.10—67.6
BIOCLIPZero-shot=true, Visual Encoder=ViT-B/162025.10—58.8
BioTrove-CLIPZero-shot=true, Visual Encoder=ViT-B/162025.10—39.4
BYOLBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—72.54
BYOL+CVSABackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—73.75
BYOL+DiLoBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—73.12
CLIP (ViT-B/16)Zero-shot=true, Visual Encoder=ViT-B/162025.10—39
FG-CLIPZero-shot=true, Visual Encoder=ViT-B/162025.10—48.3
InsLocBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—72.8
LooC*Backbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—72.84
MoCo.v2Backbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—71.36
RandomBackbone=ResNet-50, Pre-training Setting=Random initialization, Evaluation Protocol=Fine-tuned2021.06—65.78
Random GuessingZero-shot=true2025.10—0.2
Rel-LocBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—72.6
Rot-PredBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—73.01
SigLIPZero-shot=true, Visual Encoder=ViT-B/162025.10—50.2
SimCLRBackbone=ResNet-50, Pre-training Setting=Second-stage only (800 epochs), Evaluation Protocol=Fine-tuned2021.06—72.05