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 66516675 of 10420 papers

TitleStatusHype
Matching Distributions via Optimal Transport for Semi-Supervised Learning0
Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation0
Model-Agnostic Learning to Meta-Learn0
Learning Equivariant RepresentationsCode1
Practical No-box Adversarial Attacks against DNNsCode1
Batch Group Normalization0
Evolving Character-Level DenseNet Architectures using Genetic Programming0
Robust Instance Segmentation through Reasoning about Multi-Object OcclusionCode1
Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models0
Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclusteringCode0
Artist, Style And Year Classification Using Face Recognition And Clustering With Convolutional Neural Networks0
Are Gradient-based Saliency Maps Useful in Deep Reinforcement Learning?0
Chair Segments: A Compact Benchmark for the Study of Object SegmentationCode0
An Once-for-All Budgeted Pruning Framework for ConvNets Considering Input Resolution0
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs0
Rethinking Skip Connection with Layer Normalization0
Adversarial Robustness Across Representation Spaces0
Data Augmentation with norm-VAE for Unsupervised Domain AdaptationCode1
Communication-Efficient Federated Distillation0
Disentangling Label Distribution for Long-tailed Visual RecognitionCode1
A Unified Deep Speaker Embedding Framework for Mixed-Bandwidth Speech Data0
Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNetsCode0
Learning Invariances in Neural Networks from Training Data0
Is normalization indispensable for training deep neural network?Code1
HRN: A Holistic Approach to One Class LearningCode1
Show:102550
← PrevPage 267 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified