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 45014550 of 10420 papers

TitleStatusHype
Heterogeneous Network Based Contrastive Learning Method for PolSAR Land Cover ClassificationCode0
A Simple Single-Scale Vision Transformer for Object Localization and Instance SegmentationCode0
Continual Adaptation of Vision Transformers for Federated LearningCode0
Conditional Variance Penalties and Domain Shift RobustnessCode0
HDKD: Hybrid Data-Efficient Knowledge Distillation Network for Medical Image ClassificationCode0
Fine-Grained Scene Image Classification with Modality-Agnostic AdapterCode0
Activation Function Optimization Scheme for Image ClassificationCode0
Fine-grained Optimization of Deep Neural NetworksCode0
Cooperative Meta-Learning with Gradient AugmentationCode0
Learning Activation Functions to Improve Deep Neural NetworksCode0
HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual RecognitionCode0
Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and BeyondCode0
Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail RecognitionCode0
Glyce: Glyph-vectors for Chinese Character RepresentationsCode0
Fine-Grained ImageNet Classification in the WildCode0
Harnessing the Power of Infinitely Wide Deep Nets on Small-data TasksCode0
Harnessing Adversarial Distances to Discover High-Confidence ErrorsCode0
Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge EnsemblesCode0
AOGNets: Compositional Grammatical Architectures for Deep LearningCode0
Learning deep illumination-robust features from multispectral filter array imagesCode0
Core Tokensets for Data-efficient Sequential Training of TransformersCode0
Hardware Acceleration for Real-Time Wildfire Detection Onboard Drone NetworksCode0
Hardware Resilience Properties of Text-Guided Image ClassifiersCode0
Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network WatermarkingCode0
ConDiSR: Contrastive Disentanglement and Style Regularization for Single Domain GeneralizationCode0
Hard Negative Sample Mining for Whole Slide Image ClassificationCode0
A Bayesian Evaluation Framework for Subjectively Annotated Visual Recognition TasksCode0
Attention-Based Deep Neural Networks for Detection of Cancerous and Precancerous Esophagus Tissue on Histopathological SlidesCode0
CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded SystemsCode0
HaSPeR: An Image Repository for Hand Shadow Puppet RecognitionCode0
Hiera: A Hierarchical Vision Transformer without the Bells-and-WhistlesCode0
Towards Context-Agnostic Learning Using Synthetic DataCode0
Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural NetworksCode0
Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter SamplerCode0
Filtering Empty Camera Trap Images in Embedded SystemsCode0
A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer LearningCode0
Correlation-Based Band Selection for Hyperspectral Image ClassificationCode0
Learning Hyperparameters via a Data-Emphasized Variational ObjectiveCode0
A Simple Approach to Adversarial Robustness in Few-shot Image ClassificationCode0
Guarantees of confidentiality via Hammersley-Chapman-Robbins boundsCode0
Growing a Brain with Sparsity-Inducing Generation for Continual LearningCode0
Learning in Deep Factor Graphs with Gaussian Belief PropagationCode0
GANchors: Realistic Image Perturbation Distributions for Anchors Using Generative ModelsCode0
Fidelity Estimation Improves Noisy-Image Classification With Pretrained NetworksCode0
Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial AttacksCode0
Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and TransparencyCode0
Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene ImagesCode0
A Signal Propagation Perspective for Pruning Neural Networks at InitializationCode0
Group Downsampling with Equivariant Anti-aliasingCode0
Concept Graph Embedding Models for Enhanced Accuracy and InterpretabilityCode0
Show:102550
← PrevPage 91 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