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 801825 of 10419 papers

TitleStatusHype
TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and GeneralizationCode1
Understanding the Role of the Projector in Knowledge DistillationCode1
DiffMIC: Dual-Guidance Diffusion Network for Medical Image ClassificationCode1
Uncertainty-informed Mutual Learning for Joint Medical Image Classification and SegmentationCode1
The Cascaded Forward Algorithm for Neural Network TrainingCode1
Rethinking Model Ensemble in Transfer-based Adversarial AttacksCode1
A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain AdaptationCode1
DeepMIM: Deep Supervision for Masked Image ModelingCode1
Making Vision Transformers Efficient from A Token Sparsification ViewCode1
Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image ClassificationCode1
Twin Contrastive Learning with Noisy LabelsCode1
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReIDCode1
Pretrained ViTs Yield Versatile Representations For Medical ImagesCode1
FireRisk: A Remote Sensing Dataset for Fire Risk Assessment with Benchmarks Using Supervised and Self-supervised LearningCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Schema Inference for Interpretable Image ClassificationCode1
Spawrious: A Benchmark for Fine Control of Spurious Correlation BiasesCode1
FFT-based Dynamic Token Mixer for VisionCode1
A Unified Algebraic Perspective on Lipschitz Neural NetworksCode1
EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled RegularizationCode1
Structure Pretraining and Prompt Tuning for Knowledge Graph TransferCode1
Improving GAN Training via Feature Space ShrinkageCode1
Time Series as Images: Vision Transformer for Irregularly Sampled Time SeriesCode1
GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic ForgettingCode1
Generic-to-Specific Distillation of Masked AutoencodersCode1
Show:102550
← PrevPage 33 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