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 6601–6625 of 10420 papers

TitleStatusHype
mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets—0
CosSGD: Communication-Efficient Federated Learning with a Simple Cosine-Based Quantization—0
Application of the Neural Network Dependability Kit in Real-World Environments—0
Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification—0
DSM Refinement with Deep Encoder-Decoder Networks—0
Improving model calibration with accuracy versus uncertainty optimizationCode0
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPUCode1
Graphs for deep learning representations—0
WILDS: A Benchmark of in-the-Wild Distribution ShiftsCode1
Aggregative Self-Supervised Feature Learning from a Limited Sample—0
Privacy-preserving Decentralized Aggregation for Federated Learning—0
EfficientPose: Efficient Human Pose Estimation with Neural Architecture SearchCode1
Extended Few-Shot Learning: Exploiting Existing Resources for Novel TasksCode1
Attentional-Biased Stochastic Gradient DescentCode1
Delay Differential Neural Networks—0
Learning Consistent Deep Generative Models from Sparse Data via Prediction Constraints—0
Assessing The Importance Of Colours For CNNs In Object Recognition—0
Multi-direction Networks with Attentional Spectral Prior for Hyperspectral Image ClassificationCode1
Avoiding The Double Descent Phenomenon of Random Feature Models Using Hybrid RegularizationCode0
ALReLU: A different approach on Leaky ReLU activation function to improve Neural Networks PerformanceCode0
Dependency Decomposition and a Reject Option for Explainable Models—0
Cyclic orthogonal convolutions for long-range integration of features—0
Confidence Estimation via Auxiliary Models—0
Comparison of Update and Genetic Training Algorithms in a Memristor Crossbar Perceptron—0
Distant Domain Transfer Learning for Medical Imaging—0
Show:102550
← PrevPage 265 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