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 18761900 of 10420 papers

TitleStatusHype
On Robustness and Transferability of Convolutional Neural NetworksCode1
OccamNet: A Fast Neural Model for Symbolic Regression at ScaleCode1
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
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
Patch-wise Attack for Fooling Deep Neural NetworkCode1
Concept Learners for Few-Shot LearningCode1
Learning to Learn Parameterized Classification Networks for Scalable Input ImagesCode1
Temporal Self-Ensembling Teacher for Semi-Supervised Object DetectionCode1
Adversarially-Trained Deep Nets Transfer Better: Illustration on Image ClassificationCode1
Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural NetworksCode1
AdaScale SGD: A User-Friendly Algorithm for Distributed TrainingCode1
Attack of the Tails: Yes, You Really Can Backdoor Federated LearningCode1
Generalized Few-Shot Video Classification with Video Retrieval and Feature GenerationCode1
Dynamic Group Convolution for Accelerating Convolutional Neural NetworksCode1
Discretization-Aware Architecture SearchCode1
SpinalNet: Deep Neural Network with Gradual InputCode1
GOLD-NAS: Gradual, One-Level, DifferentiableCode1
Adaptive Risk Minimization: Learning to Adapt to Domain ShiftCode1
Self-Challenging Improves Cross-Domain GeneralizationCode1
Rethinking Channel Dimensions for Efficient Model DesignCode1
Measuring Robustness to Natural Distribution Shifts in Image ClassificationCode1
Early-Learning Regularization Prevents Memorization of Noisy LabelsCode1
Ontology-guided Semantic Composition for Zero-Shot LearningCode1
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over ModulesCode1
Show:102550
← PrevPage 76 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