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 101125 of 10419 papers

TitleStatusHype
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality InversionCode2
LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual TasksCode2
Practical Continual Forgetting for Pre-trained Vision ModelsCode2
Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal UnderstandingCode2
TakuNet: an Energy-Efficient CNN for Real-Time Inference on Embedded UAV systems in Emergency Response ScenariosCode2
MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image ClassificationCode2
FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation LearningCode2
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge DistillationCode2
2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image ClassificationCode2
Task Singular Vectors: Reducing Task Interference in Model MergingCode2
TinyViM: Frequency Decoupling for Tiny Hybrid Vision MambaCode2
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space DualityCode2
BiomedCoOp: Learning to Prompt for Biomedical Vision-Language ModelsCode2
ScaleKD: Strong Vision Transformers Could Be Excellent TeachersCode2
Frontiers in Intelligent ColonoscopyCode2
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State FusionCode2
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet UpcyclingCode2
One missing piece in Vision and Language: A Survey on Comics UnderstandingCode2
A Survey on Mixup Augmentations and BeyondCode2
PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease SegmentationCode2
The AdEMAMix Optimizer: Better, Faster, OlderCode2
3D-RCNet: Learning from Transformer to Build a 3D Relational ConvNet for Hyperspectral Image ClassificationCode2
HAIR: Hypernetworks-based All-in-One Image RestorationCode2
SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-trainingCode2
CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile ApplicationsCode2
Show:102550
← PrevPage 5 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
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