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 63516375 of 10420 papers

TitleStatusHype
Momentum Residual Neural NetworksCode1
Learning image quality assessment by reinforcing task amenable data selection0
OntoZSL: Ontology-enhanced Zero-shot LearningCode1
Cross-modal Adversarial ReprogrammingCode1
Perceptually Constrained Adversarial Attacks0
Naturalizing Neuromorphic Vision Event Streams Using GANs0
Segmenting two-dimensional structures with strided tensor networksCode0
Multi-class Generative Adversarial Nets for Semi-supervised Image Classification0
Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization0
Bayesian Neural Network Priors RevisitedCode1
A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes0
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-TuningCode1
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text SupervisionCode2
High-Performance Large-Scale Image Recognition Without NormalizationCode1
Clusterability as an Alternative to Anchor Points When Learning with Noisy LabelsCode1
BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionCode1
Detecting Localized Adversarial Examples: A Generic Approach using Critical Region Analysis0
Training Vision Transformers for Image RetrievalCode1
Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels0
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural networkCode1
Negative Data AugmentationCode1
Distribution Adaptive INT8 Quantization for Training CNNs0
DetCo: Unsupervised Contrastive Learning for Object DetectionCode1
WheaCha: A Method for Explaining the Predictions of Models of Code0
Rationally Inattentive Utility Maximization for Interpretable Deep Image ClassificationCode0
Show:102550
← PrevPage 255 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