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 41514175 of 10420 papers

TitleStatusHype
QSAN: A Near-term Achievable Quantum Self-Attention Network0
Tree Structure-Aware Few-Shot Image Classification via Hierarchical AggregationCode1
Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing0
Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationCode0
Adversarial Robustness Assessment of NeuroEvolution Approaches0
LightViT: Towards Light-Weight Convolution-Free Vision TransformersCode1
Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial ScenariosCode2
Regression Metric Loss: Learning a Semantic Representation Space for Medical ImagesCode1
UniNet: Unified Architecture Search with Convolution, Transformer, and MLPCode1
Backdoor Attacks on Crowd CountingCode1
Look-ups are not (yet) all you need for deep learning inferenceCode0
Contrastive Deep SupervisionCode1
Image and Model Transformation with Secret Key for Vision Transformer0
RE-Tagger: A light-weight Real-Estate Image Classifier0
Wave-ViT: Unifying Wavelet and Transformers for Visual Representation LearningCode2
Adversarial Style Augmentation for Domain Generalized Urban-Scene SegmentationCode0
Adaptive Fine-Grained Predicates Learning for Scene Graph Generation0
PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification0
Facilitated machine learning for image-based fruit quality assessmentCode0
Rethinking Persistent Homology for Visual Recognition0
SiaTrans: Siamese Transformer Network for RGB-D Salient Object Detection with Depth Image Classification0
Towards a More Rigorous Science of Blindspot Discovery in Image Classification ModelsCode1
Combining Deep Learning with Good Old-Fashioned Machine Learning0
On the Subspace Structure of Gradient-Based Meta-Learning0
Guiding the retraining of convolutional neural networks against adversarial inputs0
Show:102550
← PrevPage 167 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified