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 891900 of 10420 papers

TitleStatusHype
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural NetworksCode1
fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functionsCode1
Combating Label Noise in Deep Learning Using AbstentionCode1
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel SizesCode1
Embedded Prompt Tuning: Towards Enhanced Calibration of Pretrained Models for Medical ImagesCode1
Communication-Efficient Federated Learning Based on Explanation-Guided Pruning for Remote Sensing Image ClassificationCode1
Adversarial AutoMixupCode1
Compositional Explanations of NeuronsCode1
FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image ClassificationCode1
DenoiseRep: Denoising Model for Representation LearningCode1
Show:102550
← PrevPage 90 of 1042Next →

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