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 901925 of 10419 papers

TitleStatusHype
POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator0
FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image ClassificationCode0
Vision-Language Models are Strong Noisy Label DetectorsCode1
All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path AggregationCode1
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet UpcyclingCode2
On the universality of neural encodings in CNNs0
Learning to Obstruct Few-Shot Image Classification over Restricted ClassesCode0
Cauchy activation function and XNet0
Accelerating Malware Classification: A Vision Transformer SolutionCode0
Deep Hybrid Architecture for Very Low-Resolution Image Classification Using Capsule AttentionCode0
Unconditional stability of a recurrent neural circuit implementing divisive normalizationCode0
Med-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation0
Towards the Mitigation of Confirmation Bias in Semi-supervised Learning: a Debiased Training Perspective0
Realistic Evaluation of Model Merging for Compositional GeneralizationCode1
Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoECode1
Byzantine-Robust Aggregation for Securing Decentralized Federated LearningCode0
Cascade Prompt Learning for Vision-Language Model AdaptationCode3
Let the Quantum Creep In: Designing Quantum Neural Network Models by Gradually Swapping Out Classical ComponentsCode0
DARE: Diverse Visual Question Answering with Robustness Evaluation0
SSP-RACL: Classification of Noisy Fundus Images with Self-Supervised Pretraining and Robust Adaptive Credal Loss0
Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks0
Stochastic Subsampling With Average Pooling0
HVT: A Comprehensive Vision Framework for Learning in Non-Euclidean SpaceCode1
Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN RobustnessCode0
Accumulator-Aware Post-Training Quantization0
Show:102550
← PrevPage 37 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
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