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 13261350 of 10420 papers

TitleStatusHype
FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel RepresentationCode1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
Multi-Scale High-Resolution Vision Transformer for Semantic SegmentationCode1
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?Code1
Explaining Latent Representations with a Corpus of ExamplesCode1
MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep LearningCode1
Physically Explainable CNN for SAR Image ClassificationCode1
Towards artificial general intelligence via a multimodal foundation modelCode1
On sensitivity of meta-learning to support dataCode1
Stable Anderson Acceleration for Deep LearningCode1
ZerO Initialization: Initializing Neural Networks with only Zeros and OnesCode1
Instance-Conditional Knowledge Distillation for Object DetectionCode1
MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited LabelsCode1
Sinkformers: Transformers with Doubly Stochastic AttentionCode1
Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer AggregationCode1
A Simple Baseline for Low-Budget Active LearningCode1
Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image ClassificationCode1
Learning Partial Equivariances from DataCode1
Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic OptimizationCode1
HRFormer: High-Resolution Transformer for Dense PredictionCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel SizesCode1
Reliable Deep Learning Plant Leaf Disease Classification Based on Light-Chroma Separated BranchesCode1
Self-Supervised Learning by Estimating Twin Class DistributionsCode1
FocusNet: Classifying Better by Focusing on Confusing ClassesCode1
Show:102550
← PrevPage 54 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