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 51100 of 10419 papers

TitleStatusHype
Vision Transformers: From Semantic Segmentation to Dense PredictionCode3
XCiT: Cross-Covariance Image TransformersCode3
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked ModelingCode3
Detecting Twenty-thousand Classes using Image-level SupervisionCode3
Demystify Mamba in Vision: A Linear Attention PerspectiveCode3
VisionLLaMA: A Unified LLaMA Backbone for Vision TasksCode3
Vision-Language Pre-training: Basics, Recent Advances, and Future TrendsCode3
xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba CounterpartCode3
Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN TicketCode3
EfficientNetV2: Smaller Models and Faster TrainingCode3
SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation ImageryCode3
TCFormer: Visual Recognition via Token Clustering TransformerCode3
ResNeSt: Split-Attention NetworksCode3
PlainMamba: Improving Non-Hierarchical Mamba in Visual RecognitionCode3
Datasets: A Community Library for Natural Language ProcessingCode3
Transformers in Medical Imaging: A SurveyCode3
ADOPT: Modified Adam Can Converge with Any β_2 with the Optimal RateCode3
ONE-PEACE: Exploring One General Representation Model Toward Unlimited ModalitiesCode3
Patches Are All You Need?Code3
Cascade Prompt Learning for Vision-Language Model AdaptationCode3
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile DevicesCode3
Momentum Contrast for Unsupervised Visual Representation LearningCode3
MTP: Advancing Remote Sensing Foundation Model via Multi-Task PretrainingCode3
U^2-Net: Going Deeper with Nested U-Structure for Salient Object DetectionCode3
MetaFormer Baselines for VisionCode3
MaxViT: Multi-Axis Vision TransformerCode3
MiniViT: Compressing Vision Transformers with Weight MultiplexingCode3
Ludwig: a type-based declarative deep learning toolboxCode3
Bag of Freebies for Training Object Detection Neural NetworksCode3
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMsCode3
5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition TasksCode3
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive SurveyCode3
FusionBench: A Comprehensive Benchmark of Deep Model FusionCode3
QOC: Quantum On-Chip Training with Parameter Shift and Gradient PruningCode3
Falcon: A Remote Sensing Vision-Language Foundation ModelCode3
FastViT: A Fast Hybrid Vision Transformer using Structural ReparameterizationCode3
AutoAugment: Learning Augmentation Policies from DataCode3
MobileNetV4 -- Universal Models for the Mobile EcosystemCode3
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image RecognitionCode3
RSMamba: Remote Sensing Image Classification with State Space ModelCode3
Separable Self-attention for Mobile Vision TransformersCode3
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space DualityCode2
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
Effective Data Augmentation With Diffusion ModelsCode2
Agent Attention: On the Integration of Softmax and Linear AttentionCode2
Efficient Multi-Scale Attention Module with Cross-Spatial LearningCode2
EMR-Merging: Tuning-Free High-Performance Model MergingCode2
Dilated Neighborhood Attention TransformerCode2
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksCode2
Show:102550
← PrevPage 2 of 209Next →

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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified