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
5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition TasksCode3
Diffusion Feedback Helps CLIP See BetterCode3
TCFormer: Visual Recognition via Token Clustering TransformerCode3
xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba CounterpartCode3
FusionBench: A Comprehensive Benchmark of Deep Model FusionCode3
Demystify Mamba in Vision: A Linear Attention PerspectiveCode3
MobileNetV4 -- Universal Models for the Mobile EcosystemCode3
RSMamba: Remote Sensing Image Classification with State Space ModelCode3
PlainMamba: Improving Non-Hierarchical Mamba in Visual RecognitionCode3
MTP: Advancing Remote Sensing Foundation Model via Multi-Task PretrainingCode3
VisionLLaMA: A Unified LLaMA Backbone for Vision TasksCode3
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive SurveyCode3
Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN TicketCode3
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile DevicesCode3
SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation ImageryCode3
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image RecognitionCode3
ONE-PEACE: Exploring One General Representation Model Toward Unlimited ModalitiesCode3
FastViT: A Fast Hybrid Vision Transformer using Structural ReparameterizationCode3
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked ModelingCode3
MetaFormer Baselines for VisionCode3
Vision-Language Pre-training: Basics, Recent Advances, and Future TrendsCode3
Vision Transformers: From Semantic Segmentation to Dense PredictionCode3
Separable Self-attention for Mobile Vision TransformersCode3
MiniViT: Compressing Vision Transformers with Weight MultiplexingCode3
MaxViT: Multi-Axis Vision TransformerCode3
Visual Prompt TuningCode3
QOC: Quantum On-Chip Training with Parameter Shift and Gradient PruningCode3
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation ModelsCode3
Patches Are All You Need?Code3
Transformers in Medical Imaging: A SurveyCode3
Detecting Twenty-thousand Classes using Image-level SupervisionCode3
Datasets: A Community Library for Natural Language ProcessingCode3
XCiT: Cross-Covariance Image TransformersCode3
EfficientNetV2: Smaller Models and Faster TrainingCode3
U^2-Net: Going Deeper with Nested U-Structure for Salient Object DetectionCode3
ResNeSt: Split-Attention NetworksCode3
Momentum Contrast for Unsupervised Visual Representation LearningCode3
Ludwig: a type-based declarative deep learning toolboxCode3
EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksCode3
Bag of Freebies for Training Object Detection Neural NetworksCode3
AutoAugment: Learning Augmentation Policies from DataCode3
GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language ModelsCode2
Optimal Weighted Convolution for Classification and DenosingCode2
Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information AnalysisCode2
Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-TuningCode2
UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly DetectionCode2
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization AlignmentCode2
Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood AttentionCode2
DAMamba: Vision State Space Model with Dynamic Adaptive ScanCode2
ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image ClassificationCode2
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