AI Paper Atlas

Research map / Benchmarks / Oxford Flowers

Oxford Flowers leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Oxford Flowers. Best accuracy: 99.64 (Diff-Mix, CVPR 2024).

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.

Oxford Flowers · accuracy

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

#accuracy ↑MethodPaperTopic
199.64Diff-Mix
ViT-B/16
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
CVPR 2024 · Table 1
Text-to-image diffusion
299EXPRES
ViT-B/16
Learning Expressive Prompting With Residuals for Vision Transformers
CVPR 2023 · FGVC results table
Attention and transformers
398.7DoRA (WT-all)
ViT-S/16
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
ICLR 2024 · text
Video segmentation and tracking
498.7AlphaNet-A6AlphaNet: Improved Training of Supernets with Alpha-Divergence
ICML 2021 · Table: Transfer learning
Neural architecture search
598.6AttentiveNAS-A6AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
CVPR 2021 · Table: Results on transfer lea
Neural architecture search
697.7CAPContext-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
AAAI 2021 · supplementary Table
CNN features
797.07TRAM-θt−1
ViT-base
TRAM: Bridging Trust Regions and Sharpness Aware Minimization
ICLR 2024 · Cross-dataset image classifica
Domain adaptation and generalization
896.86LM4CV+ESCHER
LM4CV
Self-Evolving Visual Concept Library using Vision-Language Critics
CVPR 2025 · Table 1
CLIP and zero-shot
993.26XNOR_NIL
ImageNet-1k ResNet-18 frozen encoder
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators
NeurIPS 2022 · Transfer learning table
RNNs and normalization
1091.01PEG
DeiT-Small
Vision Transformers as Probabilistic Expansion from Learngene
ICML 2024 · Table 2
Attention and transformers
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.