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 376400 of 10419 papers

TitleStatusHype
Collaborative Transformers for Grounded Situation RecognitionCode1
Combining Human Predictions with Model Probabilities via Confusion Matrices and CalibrationCode1
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label CorrectionCode1
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
CODE-CL: Conceptor-Based Gradient Projection for Deep Continual LearningCode1
A Comprehensive Empirical Evaluation on Online Continual LearningCode1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAsCode1
Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image ClassificationCode1
A Comprehensive Approach to Unsupervised Embedding Learning based on AND AlgorithmCode1
Approaching Deep Learning through the Spectral Dynamics of WeightsCode1
Co2L: Contrastive Continual LearningCode1
CNN Filter DB: An Empirical Investigation of Trained Convolutional FiltersCode1
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language ModelCode1
Co^2L: Contrastive Continual LearningCode1
CoAtNet: Marrying Convolution and Attention for All Data SizesCode1
ClusterFormer: Clustering As A Universal Visual LearnerCode1
ViViT: A Video Vision TransformerCode1
Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image ClassificationCode1
An Open-source Tool for Hyperspectral Image Augmentation in TensorflowCode1
4-bit Shampoo for Memory-Efficient Network TrainingCode1
A Partially Reversible U-Net for Memory-Efficient Volumetric Image SegmentationCode1
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep LearningCode1
CoCa: Contrastive Captioners are Image-Text Foundation ModelsCode1
Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer LearningCode1
Show:102550
← PrevPage 16 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