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 21512200 of 10419 papers

TitleStatusHype
Continual atlas-based segmentation of prostate MRICode1
Energy-Latency Attacks via Sponge PoisoningCode1
Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal RepresentationsCode1
Enhance Image Classification via Inter-Class Image Mixup with Diffusion ModelCode1
AFN: Adaptive Fusion Normalization via an Encoder-Decoder FrameworkCode1
Continual Hippocampus Segmentation with TransformersCode1
Enhancing Sharpness-Aware Optimization Through Variance SuppressionCode1
Ensembling with Deep Generative ViewsCode1
DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image ClassificationCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional NetworkCode1
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document UnderstandingCode1
Continual Learning Using a Kernel-Based Method Over Foundation ModelsCode1
Escaping the Big Data Paradigm with Compact TransformersCode1
EVA-CLIP: Improved Training Techniques for CLIP at ScaleCode1
Evaluating histopathology transfer learning with ChampKitCode1
A General Regret Bound of Preconditioned Gradient Method for DNN TrainingCode1
Evaluation of Deep Neural Network Domain Adaptation Techniques for Image RecognitionCode1
Continual Learning with Scaled Gradient ProjectionCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
Evolving Normalization-Activation LayersCode1
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision TransformerCode1
ExCon: Explanation-driven Supervised Contrastive Learning for Image ClassificationCode1
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningCode1
ConTNet: Why not use convolution and transformer at the same time?Code1
AutoAssist: A Framework to Accelerate Training of Deep Neural NetworksCode1
Discovering and Mitigating Visual Biases through Keyword ExplanationCode1
Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature AttributionCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
NoisyNN: Exploring the Impact of Information Entropy Change in Learning SystemsCode1
A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled SamplesCode1
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy LabelsCode1
Active Learning for Convolutional Neural Networks: A Core-Set ApproachCode1
FACMIC: Federated Adaptative CLIP Model for Medical Image ClassificationCode1
Contrastive Deep SupervisionCode1
Failure Detection in Medical Image Classification: A Reality Check and Benchmarking TestbedCode1
DGSSC: A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspectral ImageryCode1
DIFFender: Diffusion-Based Adversarial Defense against Patch AttacksCode1
A Survey of Classical And Quantum Sequence ModelsCode1
Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution DetectionCode1
No Routing Needed Between CapsulesCode1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding AttacksCode1
Contrastive Learning of Generalized Game RepresentationsCode1
A General Framework For Detecting Anomalous Inputs to DNN ClassifiersCode1
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text AttacksCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Detecting AutoAttack Perturbations in the Frequency DomainCode1
DEUP: Direct Epistemic Uncertainty PredictionCode1
Show:102550
← PrevPage 44 of 209Next →

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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 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