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 721730 of 10420 papers

TitleStatusHype
Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-TrainingCode1
Two-Stage Holistic and Contrastive Explanation of Image ClassificationCode1
Large-scale Dataset Pruning with Dynamic UncertaintyCode1
Improving Visual Prompt Tuning for Self-supervised Vision TransformersCode1
Multi-level Multiple Instance Learning with Transformer for Whole Slide Image ClassificationCode1
Revising deep learning methods in parking lot occupancy detectionCode1
Towards Label-free Scene Understanding by Vision Foundation ModelsCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt TuningCode1
The Information Pathways Hypothesis: Transformers are Dynamic Self-EnsemblesCode1
Show:102550
← PrevPage 73 of 1042Next →

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