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 851875 of 10419 papers

TitleStatusHype
What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias0
Time Traveling to Defend Against Adversarial Example Attacks in Image Classification0
More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed RoutingCode0
CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features0
When the Small-Loss Trick is Not Enough: Multi-Label Image Classification with Noisy Labels Applied to CCTV Sewer Inspections0
Explainability of Deep Neural Networks for Brain Tumor DetectionCode0
Optimizing Estimators of Squared Calibration Errors in Classification0
QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space ModelCode1
JPEG Inspired Deep LearningCode0
Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization0
Parameter Efficient Fine-tuning via Explained Variance AdaptationCode1
FACMIC: Federated Adaptative CLIP Model for Medical Image ClassificationCode1
NegMerge: Consensual Weight Negation for Strong Machine UnlearningCode1
Conformal Structured PredictionCode0
A second-order-like optimizer with adaptive gradient scaling for deep learningCode0
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel MachinesCode0
Core Tokensets for Data-efficient Sequential Training of TransformersCode0
Contrastive Learning to Fine-Tune Feature Extraction Models for the Visual Cortex0
Variable Resolution Pixel Quantization for Low Power Machine Vision Application on Edge0
Art Forgery Detection using Kolmogorov Arnold and Convolutional Neural Networks0
IGroupSS-Mamba: Interval Group Spatial-Spectral Mamba for Hyperspectral Image Classification0
SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image ClassificationCode1
Control-oriented Clustering of Visual Latent Representation0
LoTLIP: Improving Language-Image Pre-training for Long Text Understanding0
MECFormer: Multi-task Whole Slide Image Classification with Expert Consultation Network0
Show:102550
← PrevPage 35 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