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 9526–9550 of 10420 papers

TitleStatusHype
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root NormalizationCode0
Triagem virtual de imagens de imuno-histoquímica usando redes neurais artificiais e espectro de padrões—0
Fuzzy-Based Dialectical Non-Supervised Image Classification and Clustering—0
Progressive Neural Architecture SearchCode0
Improving End-to-End Memory Networks with Unified Weight Tying—0
Learning to Model the Tail—0
Gated Recurrent Convolution Neural Network for OCRCode0
ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases—0
Spatially-Adaptive Filter Units for Deep Neural NetworksCode0
Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial NetworksCode0
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)Code0
Exploiting Nontrivial Connectivity for Automatic Speech Recognition—0
Between-class Learning for Image ClassificationCode0
On the Robustness of Semantic Segmentation Models to Adversarial AttacksCode0
An Introduction to Deep Visual Explanation—0
ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks—0
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial ConvolutionsCode0
Context Augmentation for Convolutional Neural Networks—0
Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN—0
Tactics to Directly Map CNN graphs on Embedded FPGAsCode0
CleanNet: Transfer Learning for Scalable Image Classifier Training with Label NoiseCode1
Using KL-divergence to focus Deep Visual Explanation—0
Enhanced Attacks on Defensively Distilled Deep Neural Networks—0
Less-forgetful Learning for Domain Expansion in Deep Neural Networks—0
Zero-Shot Learning via Category-Specific Visual-Semantic Mapping—0
Show:102550
← PrevPage 382 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified