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 8301–8325 of 10420 papers

TitleStatusHype
Distilling Effective Supervision from Severe Label NoiseCode0
Global Feature Guided Local Pooling—0
Gated Linear NetworksCode0
Meta-learning algorithms for Few-Shot Computer VisionCode0
XNOR-Net++: Improved Binary Neural Networks—0
Test-Time Training with Self-Supervision for Generalization under Distribution ShiftsCode0
Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image ClassificationCode0
Fusion of Convolutional Neural Network and Statistical Features for Texture classification—0
Genetic Programming and Gradient Descent: A Memetic Approach to Binary Image ClassificationCode0
Impact of Low-bitwidth Quantization on the Adversarial Robustness for Embedded Neural Networks—0
Interpreting Undesirable Pixels for Image Classification on Black-Box Models—0
Noisy Batch Active Learning with Deterministic AnnealingCode0
Urban Sound Tagging using Convolutional Neural NetworksCode0
Two-stage Image Classification Supervised by a Single Teacher Single Student ModelCode0
Adaptive Binary-Ternary Quantization—0
Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network—0
Balanced Binary Neural Networks with Gated ResidualCode0
Diving into Optimization of Topology in Neural Networks—0
A Kolmogorov Complexity Approach to Generalization in Deep Learning—0
Non-imaging single-pixel sensing with optimized binary modulation—0
A Base Model Selection Methodology for Efficient Fine-Tuning—0
Model-Agnostic Feature Selection with Additional Mutual Information—0
Data Augmentation in Training CNNs: Injecting Noise to Images—0
Improved Training Speed, Accuracy, and Data Utilization via Loss Function Optimization—0
Adaptive Data Augmentation with Deep Parallel Generative Models—0
Show:102550
← PrevPage 333 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