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 16511675 of 10420 papers

TitleStatusHype
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep SubnetworksCode1
Spatially Consistent Representation LearningCode1
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research ChallengesCode1
Multimodal Representation Learning via Maximization of Local Mutual InformationCode1
Student-Teacher Feature Pyramid Matching for Anomaly DetectionCode1
TransBTS: Multimodal Brain Tumor Segmentation Using TransformerCode1
Spectral Tensor Train Parameterization of Deep Learning LayersCode1
VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning ChallengesCode1
Barlow Twins: Self-Supervised Learning via Redundancy ReductionCode1
Perceiver: General Perception with Iterative AttentionCode1
Augmentation Strategies for Learning with Noisy LabelsCode1
Moroccan Dialect -Darija- Open DatasetCode1
Transformer in TransformerCode1
PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset SelectionCode1
GaNDLF: A Generally Nuanced Deep Learning Framework for Scalable End-to-End Clinical Workflows in Medical ImagingCode1
Do Input Gradients Highlight Discriminative Features?Code1
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without ConvolutionsCode1
FINE Samples for Learning with Noisy LabelsCode1
MetaDelta: A Meta-Learning System for Few-shot Image ClassificationCode1
Conditional Positional Encodings for Vision TransformersCode1
Evolving Attention with Residual ConvolutionsCode1
Hard-Attention for Scalable Image ClassificationCode1
Adaptive Rational Activations to Boost Deep Reinforcement LearningCode1
Unbiased Teacher for Semi-Supervised Object DetectionCode1
Firefly Neural Architecture Descent: a General Approach for Growing Neural NetworksCode1
Show:102550
← PrevPage 67 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