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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 9876–9900 of 10420 papers

TitleStatusHype
EMNIST: an extension of MNIST to handwritten lettersCode0
A Novel Weight-Shared Multi-Stage CNN for Scale Robustness—0
Empirical Risk Minimization for Stochastic Convex Optimization: O(1/n)- and O(1/n^2)-type of Risk Bounds—0
Search Intelligence: Deep Learning For Dominant Category Prediction—0
ImageNet MPEG-7 Visual Descriptors - Technical Report—0
Fully Convolutional Architectures for Multi-Class Segmentation in Chest RadiographsCode0
Theoretical Foundations of Forward Feature Selection Methods based on Mutual Information—0
CP-decomposition with Tensor Power Method for Convolutional Neural Networks CompressionCode0
Training Group Orthogonal Neural Networks with Privileged Information—0
Regularizing Neural Networks by Penalizing Confident Output DistributionsCode0
Loss-Sensitive Generative Adversarial Networks on Lipschitz DensitiesCode0
Dirty Pixels: Towards End-to-End Image Processing and PerceptionCode0
Residual and Plain Convolutional Neural Networks for 3D Brain MRI ClassificationCode0
A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction—0
Convolutional Oriented Boundaries: From Image Segmentation to High-Level TasksCode0
Auxiliary Multimodal LSTM for Audio-visual Speech Recognition and Lipreading—0
An OpenCL(TM) Deep Learning Accelerator on Arria 10—0
Cost-Effective Active Learning for Deep Image ClassificationCode0
Deep Learning for Logo Recognition—0
Oriented Response NetworksCode0
Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses—0
Robust and Real-time Deep Tracking Via Multi-Scale Domain Adaptation—0
Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution—0
Weakly Supervised Semantic Segmentation using Web-Crawled Videos—0
Rotation equivariant vector field networksCode0
Show:102550
← PrevPage 396 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10RevCol-HTop 1 Accuracy90—Unverified