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 78017825 of 10420 papers

TitleStatusHype
Adapting Grad-CAM for Embedding NetworksCode1
Are These Birds Similar: Learning Branched Networks for Fine-grained RepresentationsCode1
Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks0
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised LearningCode1
Extending Class Activation Mapping Using Gaussian Receptive Field0
Relevance Prediction from Eye-movements Using Semi-interpretable Convolutional Neural Networks0
Towards detection and classification of microscopic foraminifera using transfer learningCode0
Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual FeaturesCode1
Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models0
Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep FeaturesCode0
Semi-supervised learning method based on predefined evenly-distributed class centroids0
Bag of Tricks for Retail Product Image ClassificationCode0
Diagnosing Colorectal Polyps in the Wild with Capsule NetworksCode1
Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data0
The Effect of Data Ordering in Image Classification0
Transferability of Adversarial Examples to Attack Cloud-based Image Classifier ServiceCode2
Fast Neural Network Adaptation via Parameter Remapping and Architecture SearchCode0
Multimodal Semantic Transfer from Text to Image. Fine-Grained Image Classification by Distributional Semantics0
Sparse Weight Activation TrainingCode1
Deceiving Image-to-Image Translation Networks for Autonomous Driving with Adversarial Perturbations0
FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning NetworkCode1
The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problemsCode0
Discrimination-aware Network Pruning for Deep Model CompressionCode1
DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification0
FrequentNet: A Novel Interpretable Deep Learning Model for Image ClassificationCode0
Show:102550
← PrevPage 313 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