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 40114020 of 10420 papers

TitleStatusHype
Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling0
Time-lapse image classification using a diffractive neural network0
PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification0
Multilayer deep feature extraction for visual texture recognition0
GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization0
Minimizing the Effect of Noise and Limited Dataset Size in Image Classification Using Depth Estimation as an Auxiliary Task with Deep Multitask Learning0
Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed LearningCode0
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language TasksCode0
Revisiting ensembling for improving the performance of deep learning models0
Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning0
Show:102550
← PrevPage 402 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
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