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 901950 of 10419 papers

TitleStatusHype
IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic SegmentationCode1
Improving Zero-shot Generalization and Robustness of Multi-modal ModelsCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
ResFormer: Scaling ViTs with Multi-Resolution TrainingCode1
Hyperbolic Contrastive Learning for Visual Representations beyond ObjectsCode1
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image ClassificationCode1
AIO-P: Expanding Neural Performance Predictors Beyond Image ClassificationCode1
Curriculum Temperature for Knowledge DistillationCode1
RankDNN: Learning to Rank for Few-shot LearningCode1
Class Adaptive Network CalibrationCode1
A Call to Reflect on Evaluation Practices for Failure Detection in Image ClassificationCode1
Cross-Domain Ensemble Distillation for Domain GeneralizationCode1
SVFormer: Semi-supervised Video Transformer for Action RecognitionCode1
ActMAD: Activation Matching to Align Distributions for Test-Time-TrainingCode1
Plug and Play Active Learning for Object DetectionCode1
Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image ClassificationCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous DataCode1
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual InformationCode1
DeepVoxNet2: Yet another CNN frameworkCode1
Improving the Computer-Aided Estimation of Ulcerative Colitis Severity According to Mayo Endoscopic Score by Using Regression-Based Deep LearningCode1
Federated Adaptive Prompt Tuning for Multi-Domain Collaborative LearningCode1
Fcaformer: Forward Cross Attention in Hybrid Vision TransformerCode1
PKCAM: Previous Knowledge Channel Attention ModuleCode1
Robust Deep Learning for Autonomous DrivingCode1
Enhancing Few-shot Image Classification with Cosine TransformerCode1
Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental SegmentationCode1
Perceptual Video Coding for Machines via Satisfied Machine Ratio ModelingCode1
Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution DetectionCode1
PAD-Net: An Efficient Framework for Dynamic NetworksCode1
Soft Augmentation for Image ClassificationCode1
Untargeted Backdoor Attack against Object DetectionCode1
Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency DomainCode1
L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep LearningCode1
FatNet: High Resolution Kernels for Classification Using Fully Convolutional Optical Neural NetworksCode1
One-Class Risk Estimation for One-Class Hyperspectral Image ClassificationCode1
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model CommunicationCode1
Revisiting Sparse Convolutional Model for Visual RecognitionCode1
Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharingCode1
Diffusion Visual Counterfactual ExplanationsCode1
Boosting vision transformers for image retrievalCode1
Unsupervised Few-Shot Image Classification by Learning Features into Clustering SpaceCode1
Standardized Medical Image Classification across Medical DisciplinesCode1
TTTFlow: Unsupervised Test-Time Training with Normalizing FlowCode1
DGSSC: A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspectral ImageryCode1
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task modelsCode1
Scaling & Shifting Your Features: A New Baseline for Efficient Model TuningCode1
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive LearningCode1
2nd Place Solution to Google Universal Image EmbeddingCode1
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for TransformersCode1
Show:102550
← PrevPage 19 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