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 84268450 of 10420 papers

TitleStatusHype
Convolutional Oriented Boundaries: From Image Segmentation to High-Level TasksCode0
Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image ClassificationCode0
An Analysis of Unsupervised Pre-training in Light of Recent AdvancesCode0
EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational DataCode0
Convolutional Oriented BoundariesCode0
Convolutional Neural Networks with Layer ReuseCode0
Manas: Mining Software Repositories to Assist AutoMLCode0
A CNN with Noise Inclined Module and Denoise Framework for Hyperspectral Image ClassificationCode0
Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep NetworksCode0
ETran: Energy-Based Transferability EstimationCode0
On the Robustness of Semantic Segmentation Models to Adversarial AttacksCode0
Estimating the Conformal Prediction Threshold from Noisy LabelsCode0
ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic SegmentationCode0
Automatic Data Augmentation via Invariance-Constrained LearningCode0
Estimated Depth Map Helps Image ClassificationCode0
Generative Image Translation for Data Augmentation in Colorectal Histopathology ImagesCode0
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural NetworkCode0
Automated Classification of Histopathology Images Using Transfer LearningCode0
Generative Max-Mahalanobis Classifiers for Image Classification, Generation and MoreCode0
Rethinking Robust Contrastive Learning from the Adversarial PerspectiveCode0
Generative Modeling Helps Weak Supervision (and Vice Versa)Code0
Error-free Training for Artificial Neural NetworkCode0
Replica Tree-based Federated Learning using Limited DataCode0
Convolutional Neural Networks for Global Human Settlements Mapping from Sentinel-2 Satellite ImageryCode0
Err on the Side of Texture: Texture Bias on Real DataCode0
Show:102550
← PrevPage 338 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
10RevCol-HTop 1 Accuracy90Unverified