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 8276–8300 of 10420 papers

TitleStatusHype
Covariance-free Partial Least Squares: An Incremental Dimensionality Reduction MethodCode0
Distributed Learning of Deep Neural Networks using Independent Subnet TrainingCode0
Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image ClassificationCode0
Tensor-based algorithms for image classificationCode0
SELF: Learning to Filter Noisy Labels with Self-Ensembling—0
Training Multiscale-CNN for Large Microscopy Image Classification in One Hour—0
A General Upper Bound for Unsupervised Domain Adaptation—0
BUZz: BUffer Zones for defending adversarial examples in image classification—0
Harnessing the Power of Infinitely Wide Deep Nets on Small-data TasksCode0
Generalization Bounds for Convolutional Neural Networks—0
An empirical study of pretrained representations for few-shot classification—0
Contextual Local Explanation for Black Box Classifiers—0
Adversarially Robust Few-Shot Learning: A Meta-Learning ApproachCode0
W-Net: A CNN-based Architecture for White Blood Cells Image ClassificationCode0
Scalable Verified Training for Provably Robust Image Classification—0
A Large-scale Study of Representation Learning with the Visual Task Adaptation BenchmarkCode0
Siamese Networks: The Tale of Two Manifolds—0
SlowMo: Improving Communication-Efficient Distributed SGD with Slow MomentumCode0
Augmenting learning using symmetry in a biologically-inspired domain—0
Design Space Exploration of Hardware Spiking Neurons for Embedded Artificial Intelligence—0
A Weakly Supervised Fine Label Classifier Enhanced by Coarse Supervision—0
Leveraging Model Interpretability and Stability to increase Model RobustnessCode0
Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification—0
AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos—0
DANet: Divergent Activation for Weakly Supervised Object LocalizationCode0
Show:102550
← PrevPage 332 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 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