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 22012250 of 10419 papers

TitleStatusHype
Feature Guided Masked Autoencoder for Self-supervised Learning in Remote SensingCode1
Contrastive Masked Autoencoders are Stronger Vision LearnersCode1
A survey on attention mechanisms for medical applications: are we moving towards better algorithms?Code1
FedBABU: Towards Enhanced Representation for Federated Image ClassificationCode1
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy LabelsCode1
FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and CorrectionCode1
Aggregated Residual Transformations for Deep Neural NetworksCode1
Controllable Orthogonalization in Training DNNsCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
FedMLP: Federated Multi-Label Medical Image Classification under Task HeterogeneityCode1
A Bregman Learning Framework for Sparse Neural NetworksCode1
FedScale: Benchmarking Model and System Performance of Federated Learning at ScaleCode1
FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model InterpolationCode1
FewSAR: A Few-shot SAR Image Classification BenchmarkCode1
Few-shot Object Detection via Feature ReweightingCode1
FewVS: A Vision-Semantics Integration Framework for Few-Shot Image ClassificationCode1
Curriculum Temperature for Knowledge DistillationCode1
FIBA: Frequency-Injection based Backdoor Attack in Medical Image AnalysisCode1
DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image ClassificationCode1
ConvMLP: Hierarchical Convolutional MLPs for VisionCode1
A Survey on Transferability of Adversarial Examples across Deep Neural NetworksCode1
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image ClassificationCode1
Fine-grained Recognition with Learnable Semantic Data AugmentationCode1
Convolutional Channel-wise Competitive Learning for the Forward-Forward AlgorithmCode1
Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained FeaturesCode1
Differentiable Top-k Classification LearningCode1
FireRisk: A Remote Sensing Dataset for Fire Risk Assessment with Benchmarks Using Supervised and Self-supervised LearningCode1
FixCaps: An Improved Capsules Network for Diagnosis of Skin CancerCode1
Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded PlatformsCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
EATFormer: Improving Vision Transformer Inspired by Evolutionary AlgorithmCode1
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel SizesCode1
Efficient Attention: Attention with Linear ComplexitiesCode1
FlowNAS: Neural Architecture Search for Optical Flow EstimationCode1
Benchmarking Pathology Feature Extractors for Whole Slide Image ClassificationCode1
Focal and Global Knowledge Distillation for DetectorsCode1
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear MapsCode1
A Call to Reflect on Evaluation Practices for Failure Detection in Image ClassificationCode1
AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecksCode1
FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image RecognitionCode1
Foundation Model Assisted Weakly Supervised Semantic SegmentationCode1
Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image ClassificationCode1
Convolutional Sequence to Sequence LearningCode1
FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image ClassificationCode1
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
Convolutional Xformers for VisionCode1
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic SparsityCode1
Open-World Semi-Supervised LearningCode1
Show:102550
← PrevPage 45 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