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 71517175 of 10420 papers

TitleStatusHype
A Bag of Visual Words Model for Medical Image Retrieval0
MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings0
Deep Learning Based Brain Tumor Segmentation: A SurveyCode1
OnlineAugment: Online Data Augmentation with Less Domain KnowledgeCode1
Improving Object Detection with Selective Self-supervised Self-training0
Partial local entropy and anisotropy in deep weight spaces0
A Differential Game Theoretic Neural Optimizer for Training Residual Networks0
Impact of base dataset design on few-shot image classification0
Prioritized Multi-Criteria Federated Learning0
A Technical Report for VIPriors Image Classification Challenge0
Generative Pretraining from PixelsCode2
OccamNet: A Fast Neural Model for Symbolic Regression at ScaleCode1
On Robustness and Transferability of Convolutional Neural NetworksCode1
Advances in Deep Learning for Hyperspectral Image Analysis--Addressing Challenges Arising in Practical Imaging Scenarios0
Camera Bias in a Fine Grained Classification Task0
Layer-Wise Adaptive Updating for Few-Shot Image Classification0
HyperTune: Dynamic Hyperparameter Tuning For Efficient Distribution of DNN Training Over Heterogeneous Systems0
Unsupervised machine learning via transfer learning and k-means clustering to classify materials image dataCode1
Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and EnsembleCode1
Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features0
Concept Learners for Few-Shot LearningCode1
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
Patch-wise Attack for Fooling Deep Neural NetworkCode1
Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack0
Temporal Self-Ensembling Teacher for Semi-Supervised Object DetectionCode1
Show:102550
← PrevPage 287 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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified