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 14011425 of 10419 papers

TitleStatusHype
Global Filter Networks for Image ClassificationCode1
GlobalMamba: Global Image Serialization for Vision MambaCode1
Going deeper with Image TransformersCode1
Benchmarking Adversarial Robustness on Image ClassificationCode1
Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness MetricsCode1
Analysis and evaluation of Deep Learning based Super-Resolution algorithms to improve performance in Low-Resolution Face RecognitionCode1
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised LearningCode1
Carrying out CNN Channel Pruning in a White BoxCode1
Category Query Learning for Human-Object Interaction ClassificationCode1
Gradient-Guided Annealing for Domain GeneralizationCode1
Capsules with Inverted Dot-Product Attention RoutingCode1
Gradient Surgery for Multi-Task LearningCode1
GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic ForgettingCode1
A Toolkit for Generating Code Knowledge GraphsCode1
A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled SamplesCode1
Graph Information Aggregation Cross-Domain Few-Shot Learning for Hyperspectral Image ClassificationCode1
CSPNet: A New Backbone that can Enhance Learning Capability of CNNCode1
Grid Saliency for Context Explanations of Semantic SegmentationCode1
Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image ClassificationCode1
AutoAssist: A Framework to Accelerate Training of Deep Neural NetworksCode1
Group Fisher Pruning for Practical Network CompressionCode1
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
Curriculum Temperature for Knowledge DistillationCode1
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)Code1
Decoupled Weight Decay RegularizationCode1
Show:102550
← PrevPage 57 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