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 70517075 of 10420 papers

TitleStatusHype
Fundamental Limits of Transfer Learning in Binary Classifications0
A Novel Site-Agnostic Multimodal Deep Learning Model to Identify Pro-Eating Disorder Content on Social Media0
On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations0
On Parameter Tuning in Meta-learning for Computer Vision0
A Novel Solution of an Elastic Net Regularization for Dementia Knowledge Discovery using Deep Learning0
Function-Space Variational Inference for Deep Bayesian Classification0
Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor0
Function-Space Regularization for Deep Bayesian Classification0
On Space Folds of ReLU Neural Networks0
On Study of the Binarized Deep Neural Network for Image Classification0
A study of the effect of JPG compression on adversarial images0
On the ability of CNNs to extract color invariant intensity based features for image classification0
OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery0
Enabling Deep Learning on Edge Devices through Filter Pruning and Knowledge Transfer0
A Framework for Generalizing Critical Heat Flux Detection Models Using Unsupervised Image-to-Image Translation0
On the benefits of robust models in modulation recognition0
On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency0
On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent0
On the Confidence of Neural Network Predictions for some NLP Tasks0
On the Convergence of Continual Learning with Adaptive Methods0
Active Generative Adversarial Network for Image Classification0
On the Convergence of Nonconvex Continual Learning with Adaptive Learning Rate0
On the Cost of Model-Serving Frameworks: An Experimental Evaluation0
EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencoder0
Fully Hyperbolic Convolutional Neural Networks0
Show:102550
← PrevPage 283 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