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 351375 of 10419 papers

TitleStatusHype
Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction UncertaintyCode1
From Pixels to Components: Eigenvector Masking for Visual Representation LearningCode1
Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning DynamicsCode1
Polynomial, trigonometric, and tropical activationsCode1
SPECIAL: Zero-shot Hyperspectral Image Classification With CLIPCode1
Communication-Efficient Federated Learning Based on Explanation-Guided Pruning for Remote Sensing Image ClassificationCode1
Merging Feed-Forward Sublayers for Compressed TransformersCode1
Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and BenchmarksCode1
Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement FilteringCode1
VisionGRU: A Linear-Complexity RNN Model for Efficient Image AnalysisCode1
Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAGCode1
Continual Learning Using a Kernel-Based Method Over Foundation ModelsCode1
Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision TasksCode1
Does VLM Classification Benefit from LLM Description Semantics?Code1
RapidNet: Multi-Level Dilated Convolution Based Mobile BackboneCode1
Revisiting Weight Averaging for Model MergingCode1
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design PatentsCode1
Sparse autoencoders reveal selective remapping of visual concepts during adaptationCode1
Dual-Branch Subpixel-Guided Network for Hyperspectral Image ClassificationCode1
Grounding Descriptions in Images informs Zero-Shot Visual RecognitionCode1
Token Cropr: Faster ViTs for Quite a Few TasksCode1
On the Performance Analysis of Momentum Method: A Frequency Domain PerspectiveCode1
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image CollectionsCode1
Spectral-Spatial Transformer with Active Transfer Learning for Hyperspectral Image ClassificationCode1
Vision Mamba Distillation for Low-resolution Fine-grained Image ClassificationCode1
Show:102550
← PrevPage 15 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