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 1030110325 of 10420 papers

TitleStatusHype
Structured Pruning and Quantization for Learned Image CompressionCode0
Why do These Match? Explaining the Behavior of Image Similarity ModelsCode0
Structured Label Inference for Visual UnderstandingCode0
Structured Knowledge Distillation for Semantic SegmentationCode0
Scene Clustering Based Pseudo-labeling Strategy for Multi-modal Aerial View Object ClassificationCode0
U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture SearchCode0
Sliced Wasserstein Discrepancy for Unsupervised Domain AdaptationCode0
UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition ModelsCode0
UFO-ViT: High Performance Linear Vision Transformer without SoftmaxCode0
VisCUIT: Visual Auditor for Bias in CNN Image ClassifierCode0
Structured Knowledge Distillation for Dense PredictionCode0
Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss WeightingCode0
Structured Generative Adversarial NetworksCode0
Ultra-low-power Image Classification on Neuromorphic HardwareCode0
Ultrasound Image Classification using ACGAN with Small Training DatasetCode0
Structured DropConnect for Uncertainty Inference in Image ClassificationCode0
Single-phase deep learning in cortico-cortical networksCode0
Weight Agnostic Neural NetworksCode0
Structured Analysis Dictionary Learning for Image ClassificationCode0
Scale-Equivariant Steerable NetworksCode0
Vision-and-Language PretrainingCode0
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 HoursCode0
Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter OptimizationCode0
Uncertainty-based Detection of Adversarial Attacks in Semantic SegmentationCode0
Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systemsCode0
Show:102550
← PrevPage 413 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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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