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 10251–10275 of 10420 papers

TitleStatusHype
Superpixelwise Low-rank Approximation based Partial Label Learning for Hyperspectral Image ClassificationCode0
Superpixelwise Low-Rank Approximation-Based Partial Label Learning for Hyperspectral Image ClassificationCode0
Who's in and who's out? A case study of multimodal CLIP-filtering in DataCompCode0
Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic DataCode0
Superpixel Contracted Graph-Based Learning for Hyperspectral Image ClassificationCode0
Truncating Wide Networks using Binary Tree ArchitecturesCode0
Scalable Bayesian neural networks by layer-wise input augmentationCode0
SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision TasksCode0
SMUG: Towards robust MRI reconstruction by smoothed unrollingCode0
TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting ModelsCode0
SmoothNets: Optimizing CNN architecture design for differentially private deep learningCode0
Supernet Training for Federated Image Classification under System HeterogeneityCode0
Test-time Training for Data-efficient UCDRCode0
Tube Convolutional Neural Network (T-CNN) for Action Detection in VideosCode0
Video-based Cross-modal Auxiliary Network for Multimodal Sentiment AnalysisCode0
Video Classification with Channel-Separated Convolutional NetworksCode0
Super-Efficient Super Resolution for Fast Adversarial Defense at the EdgeCode0
Subspace Inference for Bayesian Deep LearningCode0
Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network ModelsCode0
Weakly Supervised Patch Label Inference Networks for Efficient Pavement Distress Detection and Recognition in the WildCode0
Subspace Adaptation Prior for Few-Shot LearningCode0
Smooth Deep SaliencyCode0
ScaleNet: Scale Invariance Learning in Directed GraphsCode0
Small Sample Hyperspectral Image Classification Based on the Random Patches Network and Recursive FilteringCode0
Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural NetworksCode0
Show:102550
← PrevPage 411 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