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 87018725 of 10420 papers

TitleStatusHype
Training Quantized Neural Networks with a Full-precision Auxiliary Module0
SRM : A Style-based Recalibration Module for Convolutional Neural NetworksCode0
DetNAS: Backbone Search for Object DetectionCode0
Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI gamesCode0
A geometry-inspired decision-based attackCode0
On evaluating CNN representations for low resource medical image classification0
Improving Sample Complexity with Observational Supervision0
Micro-Batch Training with Batch-Channel Normalization and Weight StandardizationCode0
The LogBarrier adversarial attack: making effective use of decision boundary informationCode0
Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework0
Automated Classification of Histopathology Images Using Transfer LearningCode0
Joint Learning of Discriminative Low-dimensional Image Representations Based on Dictionary Learning and Two-layer Orthogonal Projections0
1D-Convolutional Capsule Network for Hyperspectral Image Classification0
sharpDARTS: Faster and More Accurate Differentiable Architecture SearchCode0
Enhancing Generalization of First-Order Meta-Learning0
Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image ClassificationCode0
Calibrated Top-1 Uncertainty estimates for classification by score based modelsCode0
Learning Disentangled Representations of Satellite Image Time Series0
Deep Octonion Networks0
Convolution with even-sized kernels and symmetric paddingCode0
Probabilistic End-to-end Noise Correction for Learning with Noisy LabelsCode0
Class-incremental Learning via Deep Model ConsolidationCode0
Low-Rank Discriminative Least Squares Regression for Image Classification0
Fisher Discriminative Least Squares Regression for Image ClassificationCode0
An Effective Label Noise Model for DNN Text Classification0
Show:102550
← PrevPage 349 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