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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 6201–6225 of 10420 papers

TitleStatusHype
Learning to Detect Blue-white Structures in Dermoscopy Images with Weak Supervision—0
Learning to Complement with Multiple Humans—0
Beyond Size and Class Balance: Alpha as a New Dataset Quality Metric for Deep Learning—0
Learning to combine foveal glimpses with a third-order Boltzmann machine—0
Learning To Collaborate in Decentralized Learning of Personalized Models—0
Learning to Classify New Foods Incrementally Via Compressed Exemplars—0
Detecting Adversaries, yet Faltering to Noise? Leveraging Conditional Variational AutoEncoders for Adversary Detection in the Presence of Noisy Images—0
MDL-NAS: A Joint Multi-Domain Learning Framework for Vision Transformer—0
Learning to be Global Optimizer—0
Learning to aggregate feature representations—0
Detecting Adversarial Perturbations with Saliency—0
Efficient Object Embedding for Spliced Image Retrieval—0
Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation—0
Learning to Adapt Category Consistent Meta-Feature of CLIP for Few-Shot Classification—0
Detecting Adversarial Perturbations Through Spatial Behavior in Activation Spaces—0
Learning Through Guidance: Knowledge Distillation for Endoscopic Image Classification—0
Learning The Structure of Deep Convolutional Networks—0
Measuring the Success of Diffusion Models at Imitating Human Artists—0
Beyond Linearity: Squeeze-and-Recalibrate Blocks for Few-Shot Whole Slide Image Classification—0
MECFormer: Multi-task Whole Slide Image Classification with Expert Consultation Network—0
Detecting Adversarial Examples in Convolutional Neural Networks—0
Learning the Connections in Direct Feedback Alignment—0
Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis—0
Beyond Inference: Performance Analysis of DNN Server Overheads for Computer Vision—0
Learning Task-Independent Game State Representations from Unlabeled Images—0
Show:102550
← PrevPage 249 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified