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 91519175 of 10420 papers

TitleStatusHype
GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardware0
CurriculumNet: Weakly Supervised Learning from Large-Scale Web ImagesCode0
The Quest for the Golden Activation Function0
Binarized Convolutional Neural Networks for Efficient Inference on GPUs0
Efficient Progressive Neural Architecture Search0
MnasNet: Platform-Aware Neural Architecture Search for MobileCode1
Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured DataCode0
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture DesignCode1
Improving Transferability of Deep Neural Networks0
Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classification0
HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning0
Comparator Networks0
Extreme Network Compression via Filter Group Approximation0
MaskConnect: Connectivity Learning by Gradient Descent0
Improving High Resolution Histology Image Classification with Deep Spatial Fusion Network0
Influence of Image Classification Accuracy on Saliency Map EstimationCode0
A Unified Approximation Framework for Compressing and Accelerating Deep Neural Networks0
Aggregated Learning: A Deep Learning Framework Based on Information-Bottleneck Vector Quantization0
Effects of Degradations on Deep Neural Network ArchitecturesCode0
End-to-End Incremental LearningCode1
How good is my GAN?0
Residual Network based Aggregation Model for Skin Lesion Classification0
Self-Paced Learning with Adaptive Deep Visual EmbeddingsCode0
From Volcano to Toyshop: Adaptive Discriminative Region Discovery for Scene RecognitionCode0
Recent Advances in Convolutional Neural Network Acceleration0
Show:102550
← PrevPage 367 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