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 25512575 of 10420 papers

TitleStatusHype
Multi-Receiver Task-Oriented Communications via Multi-Task Deep Learning0
Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning0
Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy MinimizationCode1
Contrastive Bi-Projector for Unsupervised Domain AdaptionCode0
Distance Matters For Improving Performance Estimation Under Covariate ShiftCode0
Robustness Stress Testing in Medical Image ClassificationCode0
SimMatchV2: Semi-Supervised Learning with Graph ConsistencyCode1
Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks0
Neural Networks at a Fraction with Pruned Quaternions0
TorchQL: A Programming Framework for Integrity Constraints in Machine Learning0
Gated Attention Coding for Training High-performance and Efficient Spiking Neural NetworksCode1
DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut LearningCode0
Distributionally Robust Optimization and Invariant Representation Learning for Addressing Subgroup Underrepresentation: Mechanisms and Limitations0
Target Detection on Hyperspectral Images Using MCMC and VI Trained Bayesian Neural Networks0
Scale-Preserving Automatic Concept Extraction (SPACE)Code0
Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative EvaluationCode0
Spintronics for image recognition: performance benchmarking via ultrafast data-driven simulations0
Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image ClassificationCode1
Robust Asymmetric Loss for Multi-Label Long-Tailed LearningCode1
End-to-End Optimization of JPEG-Based Deep Learning Process for Image Classification0
FPGA Resource-aware Structured Pruning for Real-Time Neural Networks0
Spatial Gated Multi-Layer Perceptron for Land Use and Land Cover MappingCode1
Which Tokens to Use? Investigating Token Reduction in Vision TransformersCode1
Multiscale patch-based feature graphs for image classificationCode0
Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time DetectionCode0
Show:102550
← PrevPage 103 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