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 15011525 of 10420 papers

TitleStatusHype
BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained DevicesCode1
BiTr-Unet: a CNN-Transformer Combined Network for MRI Brain Tumor SegmentationCode1
A Closer Look at Self-Supervised Lightweight Vision TransformersCode1
Deep Transferring QuantizationCode1
Faster Meta Update Strategy for Noise-Robust Deep LearningCode1
Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative StudyCode1
Black-box Few-shot Knowledge DistillationCode1
Denoised Smoothing: A Provable Defense for Pretrained ClassifiersCode1
Carrying out CNN Channel Pruning in a White BoxCode1
UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue SegmentationCode1
Addressing Failure Prediction by Learning Model ConfidenceCode1
Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box AttacksCode1
Causal Transportability for Visual RecognitionCode1
Match Them Up: Visually Explainable Few-shot Image ClassificationCode1
Fast Hierarchical Games for Image ExplanationsCode1
DeepViT: Towards Deeper Vision TransformerCode1
DeepVoxNet2: Yet another CNN frameworkCode1
MaxQ: Multi-Axis Query for N:M Sparsity NetworkCode1
Capsule Network based Contrastive Learning of Unsupervised Visual RepresentationsCode1
DeiT III: Revenge of the ViTCode1
"BNN - BN = ?": Training Binary Neural Networks without Batch NormalizationCode1
Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image ClassificationCode1
Fast and Private Inference of Deep Neural Networks by Co-designing Activation FunctionsCode1
Fast AutoAugmentCode1
Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance LearningCode1
Show:102550
← PrevPage 61 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