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 476500 of 10419 papers

TitleStatusHype
Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus ImagesCode1
Differentiable Model Scaling using Differentiable TopkCode1
TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable PromptCode1
Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image ClassificationCode1
Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature AttributionCode1
Spectral-Spatial Mamba for Hyperspectral Image ClassificationCode1
Leveraging Cross-Modal Neighbor Representation for Improved CLIP ClassificationCode1
Rethinking model prototyping through the MedMNIST+ dataset collectionCode1
CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision ModelsCode1
Pyramid Hierarchical Transformer for Hyperspectral Image ClassificationCode1
A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba ModelsCode1
Next Generation Loss Function for Image ClassificationCode1
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image ClassificationCode1
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image ClassificationCode1
Variational Stochastic Gradient Descent for Deep Neural NetworksCode1
PairAug: What Can Augmented Image-Text Pairs Do for Radiology?Code1
Label Propagation for Zero-shot Classification with Vision-Language ModelsCode1
Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive LearningCode1
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed DatasetsCode1
Improving Visual Recognition with Hyperbolical Visual Hierarchy MappingCode1
Can Biases in ImageNet Models Explain Generalization?Code1
Learn "No" to Say "Yes" Better: Improving Vision-Language Models via NegationsCode1
Enhance Image Classification via Inter-Class Image Mixup with Diffusion ModelCode1
Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design ApproachCode1
Targeted Visualization of the Backbone of Encoder LLMsCode1
Show:102550
← PrevPage 20 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