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 75017525 of 10420 papers

TitleStatusHype
Packet2Vec: Utilizing Word2Vec for Feature Extraction in Packet DataCode1
A Fast 3D CNN for Hyperspectral Image ClassificationCode1
WoodFisher: Efficient Second-Order Approximation for Neural Network CompressionCode1
Deepfake Video Forensics based on Transfer Learning0
VGGSound: A Large-scale Audio-Visual DatasetCode1
Minority Reports Defense: Defending Against Adversarial Patches0
Integration of Leaky-Integrate-and-Fire-Neurons in Deep Learning ArchitecturesCode0
Pseudo Rehearsal using non photo-realistic images0
Identification of Cervical Pathology using Adversarial Neural Networks0
Trainable Activation Function in Image Classification0
Towards Feature Space Adversarial AttackCode1
Hyperspectral Images Classification Based on Multi-scale Residual Network0
How Much Off-The-Shelf Knowledge Is Transferable From Natural Images To Pathology Images?0
RAIN: A Simple Approach for Robust and Accurate Image Classification NetworksCode0
Explicit Domain Adaptation with Loosely Coupled Samples0
Quantization of Deep Neural Networks for Accumulator-constrained Processors0
ArchNet: Data Hiding Model in Distributed Machine Learning System0
Supervised Contrastive LearningCode2
Self-supervised Learning for Astronomical Image Classification0
Deep Learning Classification With Noisy Labels0
Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning0
A review: Deep learning for medical image segmentation using multi-modality fusion0
Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network AttributionCode1
Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning0
AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image ClassificationCode1
Show:102550
← PrevPage 301 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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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