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 59265950 of 10420 papers

TitleStatusHype
Prior Gradient Mask Guided Pruning-Aware Fine-TuningCode0
Discriminability-enforcing loss to improve representation learning0
Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training BenchmarkCode0
BViT: Broad Attention based Vision TransformerCode0
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable NeuronsCode0
Fuzzy Pooling0
Exemplar-free Online Continual Learning0
Feature-level augmentation to improve robustness of deep neural networks to affine transformations0
Multi-relation Message Passing for Multi-label Text ClassificationCode0
Spherical Transformer0
Improving greedy core-set configurations for active learning with uncertainty-scaled distances0
Multi-Label Classification of Thoracic Diseases using Dense Convolutional Network on Chest RadiographsCode0
TransformNet: Self-supervised representation learning through predicting geometric transformationsCode0
Comparative Study Between Distance Measures On Supervised Optimum-Path Forest ClassificationCode0
Equivariance versus Augmentation for Spherical ImagesCode0
Methods for the frugal labeler: Multi-class semantic segmentation on heterogeneous labelsCode0
Modeling Structure with Undirected Neural NetworksCode0
If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components0
Data Consistency for Weakly Supervised Learning0
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkCode0
Corrupted Image Modeling for Self-Supervised Visual Pre-Training0
Simple Control Baselines for Evaluating Transfer Learning0
Decision boundaries and convex hulls in the feature space that deep learning functions learn from images0
Choosing an Appropriate Platform and Workflow for Processing Camera Trap Data using Artificial Intelligence0
Learning with Neighbor Consistency for Noisy Labels0
Show:102550
← PrevPage 238 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