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 826850 of 10419 papers

TitleStatusHype
Dirichlet-based Uncertainty Calibration for Active Domain AdaptationCode1
Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia EntitiesCode1
FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge ComputingCode1
Efficiency 360: Efficient Vision TransformersCode1
THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic CompressionCode1
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image ClassificationCode1
Improved Online Conformal Prediction via Strongly Adaptive Online LearningCode1
Learning with Noisy labels via Self-supervised Adversarial Noisy MaskingCode1
Learning from Noisy Labels with Decoupled Meta Label PurifierCode1
The LuViRA Dataset: Synchronized Vision, Radio, and Audio Sensors for Indoor LocalizationCode1
Reversible Vision TransformersCode1
Cross-Layer Retrospective Retrieving via Layer AttentionCode1
CHiLS: Zero-Shot Image Classification with Hierarchical Label SetsCode1
Revisiting Discriminative vs. Generative Classifiers: Theory and ImplicationsCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Hyperspectral Image Classification Using Deep Matrix CapsulesCode1
Language Quantized AutoEncoders: Towards Unsupervised Text-Image AlignmentCode1
Continual Learning with Scaled Gradient ProjectionCode1
SAAL: Sharpness-Aware Active LearningCode1
NP-Match: Towards a New Probabilistic Model for Semi-Supervised LearningCode1
UPop: Unified and Progressive Pruning for Compressing Vision-Language TransformersCode1
PhaVIP: Phage VIrion Protein classification based on chaos game representation and Vision TransformerCode1
CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image ClassificationCode1
Direct Parameterization of Lipschitz-Bounded Deep NetworksCode1
Learning to Unlearn: Instance-wise Unlearning for Pre-trained ClassifiersCode1
Show:102550
← PrevPage 34 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