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 2776–2800 of 10420 papers

TitleStatusHype
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation—0
A Novel ANN Structure for Image Recognition—0
Adversarial Attack across Datasets—0
Efficient Transformations in Deep Learning Convolutional Neural Networks—0
A novel adversarial learning strategy for medical image classification—0
Agnostic Multi-Robust Learning Using ERM—0
Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation—0
Centroid Transformers: Learning to Abstract with Attention—0
Centroid-based deep metric learning for speaker recognition—0
An Out-of-the-box Full-network Embedding for Convolutional Neural Networks—0
On the Implicit Bias Towards Minimal Depth of Deep Neural Networks—0
4Weed Dataset: Annotated Imagery Weeds Dataset—0
CELNet: Evidence Localization for Pathology Images using Weakly Supervised Learning—0
Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights—0
A Comparison of Self-Supervised Pretraining Approaches for Predicting Disease Risk from Chest Radiograph Images—0
Efficient Scale-Permuted Backbone with Learned Resource Distribution—0
An OpenCL(TM) Deep Learning Accelerator on Arria 10—0
A Non-Technical Survey on Deep Convolutional Neural Network Architectures—0
Efficient Quantum Convolutional Neural Networks for Image Classification: Overcoming Hardware Constraints—0
CE-Dedup: Cost-Effective Convolutional Neural Nets Training based on Image Deduplication—0
A Non-monotonic Smooth Activation Function—0
Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systems—0
CEC-CNN: A Consecutive Expansion-Contraction Convolutional Network for Very Small Resolution Medical Image Classification—0
A non-discriminatory approach to ethical deep learning—0
A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification—0
Show:102550
← PrevPage 112 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 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