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 576600 of 10419 papers

TitleStatusHype
Do text-free diffusion models learn discriminative visual representations?Code1
DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual ExplanationsCode1
Meta Co-Training: Two Views are Better than OneCode1
PHG-Net: Persistent Homology Guided Medical Image ClassificationCode1
Advancing Vision Transformers with Group-Mix AttentionCode1
LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual DescriptionsCode1
Benchmarking Pathology Feature Extractors for Whole Slide Image ClassificationCode1
Attention-Challenging Multiple Instance Learning for Whole Slide Image ClassificationCode1
Deep Fast Vision: A Python Library for Accelerated Deep Transfer Learning Vision PrototypingCode1
Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image ClassificationCode1
SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image ClassificationCode1
Meta-Adapter: An Online Few-shot Learner for Vision-Language ModelCode1
A Simple Interpretable Transformer for Fine-Grained Image Classification and AnalysisCode1
GTP-ViT: Efficient Vision Transformers via Graph-based Token PropagationCode1
Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLOCode1
Distilling Out-of-Distribution Robustness from Vision-Language Foundation ModelsCode1
Attention based Dual-Branch Complex Feature Fusion Network for Hyperspectral Image ClassificationCode1
InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV ImagesCode1
Continual atlas-based segmentation of prostate MRICode1
SC-MIL: Sparsely Coded Multiple Instance Learning for Whole Slide Image ClassificationCode1
Are Natural Domain Foundation Models Useful for Medical Image Classification?Code1
Analyzing Vision Transformers for Image Classification in Class Embedding SpaceCode1
Feature Guided Masked Autoencoder for Self-supervised Learning in Remote SensingCode1
Semantic Generative Augmentations for Few-Shot CountingCode1
A Survey on Transferability of Adversarial Examples across Deep Neural NetworksCode1
Show:102550
← PrevPage 24 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