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 951975 of 10419 papers

TitleStatusHype
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for TransformersCode1
SageMix: Saliency-Guided Mixup for Point CloudsCode1
WaveMix-Lite: A Resource-efficient Neural Network for Image AnalysisCode1
Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation LearningCode1
Latency-aware Spatial-wise Dynamic NetworksCode1
Token-Label Alignment for Vision TransformersCode1
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document UnderstandingCode1
STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural NetworksCode1
OPERA: Omni-Supervised Representation Learning with Hierarchical SupervisionsCode1
Understanding the Failure of Batch Normalization for Transformers in NLPCode1
Online Training Through Time for Spiking Neural NetworksCode1
Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention NetworkCode1
SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained ModelsCode1
Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image ClassificationCode1
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision ModelsCode1
Robustness Certification of Visual Perception Models via Camera Motion SmoothingCode1
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningCode1
LPT: Long-tailed Prompt Tuning for Image ClassificationCode1
Towards a Unified View on Visual Parameter-Efficient Transfer LearningCode1
OCD: Learning to Overfit with Conditional Diffusion ModelsCode1
Two-Stream Transformer for Multi-Label Image ClassificationCode1
Learning Hierarchical Image Segmentation For Recognition and By RecognitionCode1
An In-depth Study of Stochastic BackpropagationCode1
Semi-Supervised Single-View 3D Reconstruction via Prototype Shape PriorsCode1
TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video SurveillanceCode1
Show:102550
← PrevPage 39 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