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 82018225 of 10420 papers

TitleStatusHype
Regularizing Neural Networks by Penalizing Confident Output DistributionsCode0
Regularizing Neural Networks by Stochastically Training Layer EnsemblesCode0
Regularizing cross entropy loss via minimum entropy and K-L divergenceCode0
Regularized Evolution for Image Classifier Architecture SearchCode0
Regularization of Neural Networks using DropConnectCode0
Compact Bilinear PoolingCode0
Regularization-based Pruning of Irrelevant Weights in Deep Neural ArchitecturesCode0
Unsupervised Attention Mechanism across Neural Network LayersCode0
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)Code0
Sharpen Focus: Learning with Attention Separability and ConsistencyCode0
FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image ClassificationCode0
Compact and De-biased Negative Instance Embedding for Multi-Instance Learning on Whole-Slide Image ClassificationCode0
A Dynamic Reduction Network for Point CloudsCode0
Reducing Texture Bias of Deep Neural Networks via Edge Enhancing DiffusionCode0
Reducing Overlearning through Disentangled Representations by Suppressing Unknown TasksCode0
Reduced storage direct tensor ring decomposition for convolutional neural networks compressionCode0
Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural NetworksCode0
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image SegmentationCode0
FALFormer: Feature-aware Landmarks self-attention for Whole-slide Image ClassificationCode0
Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?Code0
Compact and Optimal Deep Learning with Recurrent Parameter GeneratorsCode0
FakeFormer: Efficient Vulnerability-Driven Transformers for Generalisable Deepfake DetectionCode0
Recurrent Highway Networks with Grouped Auxiliary MemoryCode0
Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline ApproachCode0
Recurrent computations for visual pattern completionCode0
Show:102550
← PrevPage 329 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