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 13761400 of 10420 papers

TitleStatusHype
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN ExecutionCode1
Federated Adaptive Prompt Tuning for Multi-Domain Collaborative LearningCode1
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural NetworksCode1
Cross-Domain Ensemble Distillation for Domain GeneralizationCode1
Bayesian Model-Agnostic Meta-LearningCode1
Bayesian Neural Network Priors RevisitedCode1
Vision Transformers with Patch DiversificationCode1
Achieving Fairness Through Channel Pruning for Dermatological Disease DiagnosisCode1
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode1
Bayesian Optimization Meets Self-DistillationCode1
Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce ClassificationCode1
IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance MattersCode1
Improving Medical Image Classification in Noisy Labels Using Only Self-supervised PretrainingCode1
Improving Object Detection by Label Assignment DistillationCode1
Improving robustness against common corruptions by covariate shift adaptationCode1
BCN: Batch Channel Normalization for Image ClassificationCode1
Cross-Iteration Batch NormalizationCode1
Cross-Layer Retrospective Retrieving via Layer AttentionCode1
Cross-modal Adversarial ReprogrammingCode1
Entropy-based Logic Explanations of Neural NetworksCode1
BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionCode1
No Routing Needed Between CapsulesCode1
InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck MambaCode1
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective AdaptationCode1
ePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill IdentificationCode1
Show:102550
← PrevPage 56 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