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 75017525 of 10420 papers

TitleStatusHype
One Weight Bitwidth to Rule Them All0
Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory0
Robustness and Overfitting Behavior of Implicit Background ModelsCode0
Graph Neural Networks for UnsupervisedDomain Adaptation of Histopathological ImageAnalytics0
A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples0
Spatial--spectral FFPNet: Attention-Based Pyramid Network for Segmentation and Classification of Remote Sensing Images0
Utilizing Explainable AI for Quantization and Pruning of Deep Neural Networks0
iCaps: An Interpretable Classifier via Disentangled Capsule Networks0
Physically-Constrained Transfer Learning through Shared Abundance Space for Hyperspectral Image Classification0
Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature AlignmentCode0
Learning Connectivity of Neural Networks from a Topological Perspective0
Correcting Data Imbalance for Semi-Supervised Covid-19 Detection Using X-ray Chest Images0
Two-phase Dynamic Routing for Micro and Macro-level Equivariance in Multi-Column Capsule NetworksCode0
Source Free Domain Adaptation with Image Translation0
Which Strategies Matter for Noisy Label Classification? Insight into Loss and Uncertainty0
Network Architecture Search for Domain Adaptation0
Can weight sharing outperform random architecture search? An investigation with TuNAS0
Deep Networks with Fast Retraining0
Single-Photon Image Classification0
A statistical theory of cold posteriors in deep neural networks0
FATNN: Fast and Accurate Ternary Neural Networks0
Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network0
Null-sampling for Interpretable and Fair RepresentationsCode0
An Efficient Confidence Measure-Based Evaluation Metric for Breast Cancer Screening Using Bayesian Neural NetworksCode0
Uncertainty Quantification using Variational Inference for Biomedical Image SegmentationCode0
Show:102550
← PrevPage 301 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