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

Showing 9761000 of 10419 papers

TitleStatusHype
EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image ClassificationCode1
Dynamic Decoupling of Placid Terminal Attractor-based Gradient Descent Algorithm0
Seam Carving as Feature Pooling in CNN0
SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values0
Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition0
Adversarial Attacks on Data AttributionCode0
Replay Consolidation with Label Propagation for Continual Object Detection0
PatchAlign:Fair and Accurate Skin Disease Image Classification by Alignment with Clinical LabelsCode1
A Survey on Mixup Augmentations and BeyondCode2
LoCa: Logit Calibration for Knowledge Distillation0
Swin Transformer for Robust Differentiation of Real and Synthetic Images: Intra- and Inter-Dataset Analysis0
Activation Function Optimization Scheme for Image ClassificationCode0
PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease SegmentationCode2
Connectivity-Inspired Network for Context-Aware RecognitionCode0
Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT ModelsCode0
WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking0
Have Large Vision-Language Models Mastered Art History?0
LowFormer: Hardware Efficient Design for Convolutional Transformer BackbonesCode1
PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised LearningCode0
The AdEMAMix Optimizer: Better, Faster, OlderCode2
Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power ApplicationsCode0
Non-Uniform Illumination Attack for Fooling Convolutional Neural NetworksCode0
iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation0
Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization0
Compressed learning based onboard semantic compression for remote sensing platformsCode0
Show:102550
← PrevPage 40 of 417Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified