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 1–10 of 10420 papers

TitleStatusHype
Automatic Classification and Segmentation of Tunnel Cracks Based on Deep Learning and Visual Explanations—0
Adversarial attacks to image classification systems using evolutionary algorithms—0
Federated Learning for Commercial Image Sources—0
Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy—0
MUPAX: Multidimensional Problem Agnostic eXplainable AI—0
Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network WatermarkingCode0
Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks—0
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise—0
ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark EvaluationCode0
Admissibility of Stein Shrinkage for Batch Normalization in the Presence of Adversarial Attacks—0
Show:102550
← PrevPage 1 of 1042Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1efficient adaptive ensemblingAccuracy99.61—Unverified
2ViT-H/14Percentage correct99.5—Unverified
3DINOv2 (ViT-g/14, frozen model, linear eval)Percentage correct99.5—Unverified
4µ2Net (ViT-L/16)Percentage correct99.49—Unverified
5ViT-L/16Percentage correct99.42—Unverified
6CaiT-M-36 U 224Percentage correct99.4—Unverified
7CvT-W24Percentage correct99.39—Unverified
8BiT-L (ResNet)Percentage correct99.37—Unverified
9RDNet-L (224 res, IN-1K pretrained)Percentage correct99.31—Unverified
10RDNet-B (224 res, IN-1K pretrained)Percentage correct99.31—Unverified