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 5175 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
Show:102550
← PrevPage 3 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