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 8501–8525 of 10420 papers

TitleStatusHype
Delving Deeper Into Astromorphic Transformers—0
Delving into Deep Image Prior for Adversarial Defense: A Novel Reconstruction-based Defense Framework—0
Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization—0
WheaCha: A Method for Explaining the Predictions of Models of Code—0
Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases—0
Demystifying Loss Functions for Classification—0
Demystifying What Code Summarization Models Learned—0
Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning—0
Denoised Labels for Financial Time-Series Data via Self-Supervised Learning—0
Denoising Mutual Knowledge Distillation in Bi-Directional Multiple Instance Learning—0
Dense Bag-of-Temporal-SIFT-Words for Time Series Classification—0
Morphological Network: How Far Can We Go with Morphological Neurons?—0
Density estimation in representation space to predict model uncertainty—0
Dependency Decomposition and a Reject Option for Explainable Models—0
DEPICT: Diffusion-Enabled Permutation Importance for Image Classification Tasks—0
Depth Estimation with Simplified Transformer—0
Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread—0
Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization—0
Depthwise-STFT based separable Convolutional Neural Networks—0
Dermoscopic Image Classification with Neural Style Transfer—0
Descriptive analysis of computational methods for automating mammograms with practical applications—0
Designing Adaptive Neural Networks for Energy-Constrained Image Classification—0
Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks—0
Design of Image Matched Non-Separable Wavelet using Convolutional Neural Network—0
Design of Real-time Semantic Segmentation Decoder for Automated Driving—0
Show:102550
← PrevPage 341 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