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 11511200 of 10419 papers

TitleStatusHype
A graph-transformer for whole slide image classificationCode1
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of EnsemblesCode1
Attentional Feature FusionCode1
"BNN - BN = ?": Training Binary Neural Networks without Batch NormalizationCode1
Dynamic Defense Against Byzantine Poisoning Attacks in Federated LearningCode1
Attention based Dual-Branch Complex Feature Fusion Network for Hyperspectral Image ClassificationCode1
Dynamic Grained Encoder for Vision TransformersCode1
Boosting Co-teaching with Compression Regularization for Label NoiseCode1
Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement FilteringCode1
A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural NetworksCode1
Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label NoiseCode1
DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data AugmentationCode1
Object Segmentation Without Labels with Large-Scale Generative ModelsCode1
AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecksCode1
Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagationCode1
AIDeveloper: deep learning image classification in life science and beyondCode1
Asymmetric Polynomial Loss For Multi-Label ClassificationCode1
Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-IdentificationCode1
AIO-P: Expanding Neural Performance Predictors Beyond Image ClassificationCode1
Bootstrap your own latent: A new approach to self-supervised LearningCode1
A Call to Reflect on Evaluation Practices for Failure Detection in Image ClassificationCode1
Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box AttacksCode1
Dynamic Graph Message Passing NetworksCode1
Robust Models Are More Interpretable Because Attributions Look NormalCode1
DynaMixer: A Vision MLP Architecture with Dynamic MixingCode1
Benchmarking Pathology Feature Extractors for Whole Slide Image ClassificationCode1
BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionCode1
Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and BeyondCode1
Asymmetric Loss For Multi-Label ClassificationCode1
Attentive Weights Generation for Few Shot Learning via Information MaximizationCode1
Attribute Descent: Simulating Object-Centric Datasets on the Content Level and BeyondCode1
EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature FusionCode1
Dual-Branch Subpixel-Guided Network for Hyperspectral Image ClassificationCode1
Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge GraphsCode1
BSRBF-KAN: A combination of B-splines and Radial Basis Functions in Kolmogorov-Arnold NetworksCode1
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantificationCode1
Engineering flexible machine learning systems by traversing functionally-invariant pathsCode1
Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal RepresentationsCode1
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt TuningCode1
Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention MechanismsCode1
DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic CalibrationCode1
Fcaformer: Forward Cross Attention in Hybrid Vision TransformerCode1
Cached Transformers: Improving Transformers with Differentiable Memory CacheCode1
Augmentation Strategies for Learning with Noisy LabelsCode1
Calibration of Neural Networks using SplinesCode1
Entropy-based Logic Explanations of Neural NetworksCode1
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural NetworkCode1
Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional NetworkCode1
CamDiff: Camouflage Image Augmentation via Diffusion ModelCode1
Better plain ViT baselines for ImageNet-1kCode1
Show:102550
← PrevPage 24 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
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