SOTAVerified

Image Classification

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Papers

Showing 31763200 of 10420 papers

TitleStatusHype
Deployment of Image Analysis Algorithms under Prevalence ShiftsCode0
Exploring the Benefits of Visual Prompting in Differential PrivacyCode0
Machine Learning for Brain Disorders: Transformers and Visual Transformers0
Boundary Unlearning0
ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked AutoencodersCode0
Creating Ensembles of Classifiers through UMDA for Aerial Scene Classification0
Bias mitigation techniques in image classification: fair machine learning in human heritage collections0
Understanding the Role of the Projector in Knowledge DistillationCode1
TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and GeneralizationCode1
Parameter-Free Channel Attention for Image Classification and Super-Resolution0
DiffMIC: Dual-Guidance Diffusion Network for Medical Image ClassificationCode1
Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond0
Uncertainty-informed Mutual Learning for Joint Medical Image Classification and SegmentationCode1
The Cascaded Forward Algorithm for Neural Network TrainingCode1
Extracting the Brain-like Representation by an Improved Self-Organizing Map for Image ClassificationCode0
A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain AdaptationCode1
Rethinking Model Ensemble in Transfer-based Adversarial AttacksCode1
Unsupervised domain adaptation by learning using privileged information0
Conditional Synthetic Food Image Generation0
Agnostic Multi-Robust Learning Using ERM0
Practicality of generalization guarantees for unsupervised domain adaptation with neural networks0
Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image ClassificationCode1
Visual Prompt Based Personalized Federated Learning0
BiFormer: Vision Transformer with Bi-Level Routing AttentionCode2
DeepMIM: Deep Supervision for Masked Image ModelingCode1
Show:102550
← PrevPage 128 of 417Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified