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 20912100 of 10420 papers

TitleStatusHype
Improved Online Conformal Prediction via Strongly Adaptive Online LearningCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Improved Generation of Adversarial Examples Against Safety-aligned LLMsCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data AugmentationCode1
IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic SegmentationCode1
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
A Simple Baseline for Low-Budget Active LearningCode1
ConvMLP: Hierarchical Convolutional MLPs for VisionCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Show:102550
← PrevPage 210 of 1042Next →

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