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 14511475 of 10420 papers

TitleStatusHype
Benchmarking Knowledge-driven Zero-shot LearningCode1
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic SparsityCode1
Multi-Compound Transformer for Accurate Biomedical Image SegmentationCode1
Co^2L: Contrastive Continual LearningCode1
R-Drop: Regularized Dropout for Neural NetworksCode1
RAILS: A Robust Adversarial Immune-inspired Learning SystemCode1
Spectral-Spatial Global Graph Reasoning for Hyperspectral Image ClassificationCode1
Can An Image Classifier Suffice For Action Recognition?Code1
SITTA: Single Image Texture Translation for Data AugmentationCode1
PVT v2: Improved Baselines with Pyramid Vision TransformerCode1
VOLO: Vision Outlooker for Visual RecognitionCode1
P2T: Pyramid Pooling Transformer for Scene UnderstandingCode1
Multi-layered Semantic Representation Network for Multi-label Image ClassificationCode1
Stateful ODE-Nets using Basis Function ExpansionsCode1
Secure Distributed Training at ScaleCode1
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?Code1
T-vMF Similarity for Regularizing Intra-Class Feature DistributionCode1
Exploring Vision Transformers for Fine-grained ClassificationCode1
Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional NetworkCode1
Contrastive Learning of Generalized Game RepresentationsCode1
How to train your ViT? Data, Augmentation, and Regularization in Vision TransformersCode1
Deep Subdomain Adaptation Network for Image ClassificationCode1
Multi-Label Learning from Single Positive LabelsCode1
Federated Semi-supervised Medical Image Classification via Inter-client Relation MatchingCode1
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective AdaptationCode1
Show:102550
← PrevPage 59 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