AI Paper Atlas

Research map / Benchmarks / Birds

Birds leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Birds. Best accuracy: 91.74 (Unary (rectifier network), NeurIPS 2022).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Birds · accuracy

11 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
191.74Unary (rectifier network)Learning Energy Networks with Generalized Fenchel-Young Losses
NeurIPS 2022 · Multilabel classification resu
Prediction and decision losses
287.4TF-MP
ResNet34
Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization
CVPR 2023 · Table 2
Zero-/few-shot and meta-learning
385.9iSICE
ResNet-50
Learning Partial Correlation Based Deep Visual Representation for Image Classification
CVPR 2023 · Table: Comparison between iSIC
CNN design
484.94DCM+SS
ResNet34
Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling
AAAI 2022 · Table: Results on Standard Ben
Zero-/few-shot and meta-learning
584.5DeepKSPD
VGG-19
DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition
ECCV 2018 · Table 1
Recognition and long-tail
676.3URTA Universal Representation Transformer Layer for Few-Shot Image Classification
ICLR 2021 · Meta-Dataset results table
Zero-/few-shot and meta-learning
774.86Shape Adaptor
VGG-16
Shape Adaptor: A Learnable Resizing Module
ECCV 2020 · Table 1
CNN design
874.24MGR (PCR+MPS)
ResNet-18
Regularizing Neural Networks with Meta-Learning Generative Models
NeurIPS 2023 · Table 1(a)
Zero-/few-shot and meta-learning
972.2CNAPS
ResNet18
Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes
NeurIPS 2019 · Table 1
Test-time adaptation
1063.29Pow-EMLR
ResNet-50
Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
ICLR 2025 · Table: Results of iSQRT-COV on
Matrix and tensor methods
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.