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 83018325 of 10420 papers

TitleStatusHype
Debiasing Classifiers by Amplifying Bias with Latent Diffusion and Large Language Models0
DebugAgent: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging0
Deceiving Google's Cloud Video Intelligence API Built for Summarizing Videos0
Deceiving Image-to-Image Translation Networks for Autonomous Driving with Adversarial Perturbations0
Decentralized Federated Learning Over Imperfect Communication Channels0
Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks0
Decentralized SGD with Over-the-Air Computation0
Decision boundaries and convex hulls in the feature space that deep learning functions learn from images0
Decision Propagation Networks for Image Classification0
Decision Tree Learning with Spatial Modal Logics0
Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features0
Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules0
Decomposition-Based Transfer Distance Metric Learning for Image Classification0
Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning0
Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks0
Deep Active Ensemble Sampling For Image Classification0
Does Deep Active Learning Work in the Wild?0
Deep Active Learning in the Open World0
Deep Active Learning in the Presence of Label Noise: A Survey0
Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks0
DeepAGREL: Biologically plausible deep learning via direct reinforcement0
Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning0
Deep Attributes from Context-Aware Regional Neural Codes0
Deep AUC Maximization for Medical Image Classification: Challenges and Opportunities0
Deep Autoencoder Model Construction Based on Pytorch0
Show:102550
← PrevPage 333 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