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 49264950 of 10420 papers

TitleStatusHype
Riemannian Nearest-Regularized Subspace Classification for Polarimetric SAR images0
A Conservative Approach for Unbiased Learning on Unknown BiasesCode1
C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic SegmentationCode2
Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition0
Learning To Collaborate in Decentralized Learning of Personalized Models0
Semi-Supervised Few-Shot Learning via Multi-Factor ClusteringCode0
Learnable Lookup Table for Neural Network QuantizationCode1
AME: Attention and Memory Enhancement in Hyper-Parameter Optimization0
Learn From Others and Be Yourself in Heterogeneous Federated LearningCode1
Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations0
Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique0
A Simple Episodic Linear Probe Improves Visual Recognition in the WildCode2
Turath-150K: Image Database of Arab Heritage0
Optimal Representations for Covariate ShiftCode1
Context-Aware Compilation of DNN Training Pipelines across Edge and CloudCode0
Improving Deep Neural Network Classification Confidence using Heatmap-based eXplainable AICode0
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Learning Spatially-Adaptive Squeeze-Excitation Networks for Image Synthesis and Image RecognitionCode0
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language ModelCode1
Super-Efficient Super Resolution for Fast Adversarial Defense at the EdgeCode0
Two-phase training mitigates class imbalance for camera trap image classification with CNNsCode0
An Empirical Study of Adder Neural Networks for Object Detection0
Vision Transformer for Small-Size DatasetsCode1
Augmenting Convolutional networks with attention-based aggregationCode1
PRIME: A few primitives can boost robustness to common corruptionsCode1
Show:102550
← PrevPage 198 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