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 68516875 of 10420 papers

TitleStatusHype
Does Data Augmentation Benefit from Split BatchNorms0
Layer-adaptive sparsity for the Magnitude-based PruningCode1
LiteDepthwiseNet: An Extreme Lightweight Network for Hyperspectral Image Classification0
Improved Multi-Source Domain Adaptation by Preservation of Factors0
QReLU and m-QReLU: Two novel quantum activation functions to aid medical diagnosticsCode1
HS-ResNet: Hierarchical-Split Block on Convolutional Neural NetworkCode1
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed GradientsCode2
Self-Supervised Domain Adaptation with Consistency TrainingCode1
Ferrograph image classification0
Effects of the Nonlinearity in Activation Functions on the Performance of Deep Learning ModelsCode0
An Evasion Attack against Stacked Capsule AutoencoderCode0
Deep Ensembles for Low-Data Transfer Learning0
Human-interpretable model explainability on high-dimensional data0
Tensor Train Factorization and Completion under Noisy Data with Prior Analysis and Rank EstimationCode0
A Very Compact Embedded CNN Processor Design Based on Logarithmic Computing0
Are all negatives created equal in contrastive instance discrimination?0
Training independent subnetworks for robust predictionVerified1
Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization0
Robust Two-Stream Multi-Feature Network for Driver Drowsiness Detection0
RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification0
Satellite Image Classification with Deep Learning0
Beyond the Attention: Distinguish the Discriminative and Confusable Features For Fine-grained Image Classification0
Shape-Texture Debiased Neural Network TrainingCode1
CC-Loss: Channel Correlation Loss For Image Classification0
Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic GraphCode0
Show:102550
← PrevPage 275 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