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 98519875 of 10420 papers

TitleStatusHype
Regularizing Neural Networks by Penalizing Confident Output DistributionsCode0
OLÉ: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep LearningCode0
OLÉ: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep LearningCode0
DBIA: Data-free Backdoor Injection Attack against Transformer NetworksCode0
Image Data Augmentation Approaches: A Comprehensive Survey and Future directionsCode0
Learning to Zoom: a Saliency-Based Sampling Layer for Neural NetworksCode0
Learning Transferable Architectures for Scalable Image RecognitionCode0
Learning Transferable Features with Deep Adaptation NetworksCode0
Dataset Distillation with Infinitely Wide Convolutional NetworksCode0
Dataset Distillation using Neural Feature RegressionCode0
A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet CategoriesCode0
Dataset Condensation with Differentiable Siamese AugmentationCode0
Dataset Condensation Driven Machine UnlearningCode0
A Computing Kernel for Network Binarization on PyTorchCode0
Data Representations' Study of Latent Image ManifoldsCode0
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual AttributesCode0
Batch-Shaping for Learning Conditional Channel Gated NetworksCode0
On adversarial training and the 1 Nearest Neighbor classifierCode0
On Batch Adaptive Training for Deep Learning: Lower Loss and Larger Step SizeCode0
Probabilistic Structural Latent Representation for Unsupervised EmbeddingCode0
Saliency-Augmented Memory Completion for Continual LearningCode0
Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT ModelsCode0
Batch-normalized Maxout Network in NetworkCode0
Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identificationCode0
Batch Model Consolidation: A Multi-Task Model Consolidation FrameworkCode0
Show:102550
← PrevPage 395 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