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 10011025 of 10419 papers

TitleStatusHype
Self-Ensembling Vision Transformer (SEViT) for Robust Medical Image ClassificationCode1
SSformer: A Lightweight Transformer for Semantic SegmentationCode1
Adaptive Edge Offloading for Image Classification Under Rate LimitCode1
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy LabelsCode1
CrAM: A Compression-Aware MinimizerCode1
Topological structure of complex predictionsCode1
Image sensing with multilayer, nonlinear optical neural networksCode1
Contrastive Masked Autoencoders are Stronger Vision LearnersCode1
Text Classification in Memristor-based Spiking Neural NetworksCode1
SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized ViolenceCode1
Visual correspondence-based explanations improve AI robustness and human-AI team accuracyCode1
Few-shot Learning with Class-Covariance Metric for Hyperspectral Image ClassificationCode1
Black-box Few-shot Knowledge DistillationCode1
Jigsaw-ViT: Learning Jigsaw Puzzles in Vision TransformerCode1
TransCL: Transformer Makes Strong and Flexible Compressive LearningCode1
Online Knowledge Distillation via Mutual Contrastive Learning for Visual RecognitionCode1
Tailoring Self-Supervision for Supervised LearningCode1
Latent Discriminant deterministic UncertaintyCode1
AutoDiCE: Fully Automated Distributed CNN Inference at the EdgeCode1
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image ClassificationCode1
Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision LearningCode1
Zero-Shot Temporal Action Detection via Vision-Language PromptingCode1
ViT-NeT: Interpretable Vision Transformers with Neural Tree DecoderCode1
Show:102550
← PrevPage 41 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