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 66766700 of 10420 papers

TitleStatusHype
Task-Oriented Feature DistillationCode1
HRN: A Holistic Approach to One Class LearningCode1
Co-Tuning for Transfer LearningCode1
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point0
Self-Supervised Generative Adversarial Compression0
SuperLoss: A Generic Loss for Robust Curriculum LearningCode1
Auto Learning AttentionCode1
Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagationCode1
Generalized Boosting0
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-trainingCode1
Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot TasksCode0
Reducing Textural Bias Improves Robustness of Deep Segmentation Models0
Scale-covariant and scale-invariant Gaussian derivative networks0
Context-aware deep model compression for edge cloud computing0
BSNet: Bi-Similarity Network for Few-shot Fine-grained Image ClassificationCode1
ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity DiscoveryCode1
Class-agnostic Object Detection0
General Multi-label Image Classification with TransformersCode1
Unsupervised part representation by Flow Capsules0
Improving Layer-wise Adaptive Rate Methods using Trust Ratio Clipping0
Regularization with Latent Space Virtual Adversarial TrainingCode1
How Well Do Self-Supervised Models Transfer?Code1
Grafit: Learning fine-grained image representations with coarse labels0
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation0
A Review of Open-World Learning and Steps Toward Open-World Learning Without LabelsCode0
Show:102550
← PrevPage 268 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
10RevCol-HTop 1 Accuracy90Unverified