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 1002610050 of 10420 papers

TitleStatusHype
The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problemsCode0
Scaling Up Semi-supervised Learning with Unconstrained Unlabelled DataCode0
The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image ClassificationCode0
The Structure Transfer Machine Theory and ApplicationsCode0
Unsupervised Deep Learning by Neighbourhood DiscoveryCode0
The Skin Game: Revolutionizing Standards for AI Dermatology Model ComparisonCode0
SGNet: A Super-class Guided Network for Image Classification and Object DetectionCode0
The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' DepthCode0
Scaling the Wild: Decentralizing Hogwild!-style Shared-memory SGDCode0
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual RepresentationsCode0
Spatial-Spectral Hyperspectral Classification based on Learnable 3D Group ConvolutionCode0
Towards Image Semantics and Syntax Sequence LearningCode0
Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image ClassificationCode0
SGML: A Symmetric Graph Metric Learning Framework for Efficient Hyperspectral Image ClassificationCode0
The Role of Subgroup Separability in Group-Fair Medical Image ClassificationCode0
The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image ClassificationCode0
Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial PerturbationsCode0
Human-in-the-loop: Towards Label Embeddings for Measuring Classification DifficultyCode0
The Pitfalls and Promise of Conformal Inference Under Adversarial AttacksCode0
Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color DistanceCode0
Towards Learning Convolutions from ScratchCode0
SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep ModelsCode0
The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scaleCode0
When do Convolutional Neural Networks Stop Learning?Code0
Visual Word Embedding for Text ClassificationCode0
Show:102550
← PrevPage 402 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