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 71267150 of 10420 papers

TitleStatusHype
Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification0
MaxDropout: Deep Neural Network Regularization Based on Maximum Output ValuesCode1
Split Computing for Complex Object Detectors: Challenges and Preliminary ResultsCode1
The MAMe Dataset: On the relevance of High Resolution and Variable Shape image propertiesCode1
Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing0
Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches0
Contraction Mapping of Feature Norms for Classifier Learning on the Data with Different Quality0
Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable ProjectionCode0
Neural networks with late-phase weightsCode0
All-Optical Information Processing Capacity of Diffractive Surfaces0
HATNet: An End-to-End Holistic Attention Network for Diagnosis of Breast Biopsy ImagesCode1
T-BFA: Targeted Bit-Flip Adversarial Weight AttackCode0
Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains0
Deep Network Ensemble Learning applied to Image Classification using CNN TreesCode1
Right for the Right Reason: Making Image Classification Robust0
DEAL: Deep Evidential Active Learning for Image ClassificationCode1
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning ApproachCode0
Multi-label Thoracic Disease Image Classification with Cross-Attention Networks0
CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution LayersCode1
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture SearchCode1
PDO-eConvs: Partial Differential Operator Based Equivariant ConvolutionsCode1
GREEN: a Graph REsidual rE-ranking Network for Grading Diabetic RetinopathyCode0
Generative Hierarchical Features from Synthesizing ImagesCode1
Survey on Deep Learning-based Kuzushiji Recognition0
A Bag of Visual Words Model for Medical Image Retrieval0
Show:102550
← PrevPage 286 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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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