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 81018125 of 10420 papers

TitleStatusHype
Dynamic Convolutions: Exploiting Spatial Sparsity for Faster InferenceCode0
3D CNN with Localized Residual Connections for Hyperspectral Image ClassificationCode0
Collective Learning0
Self-Supervised Learning of Video-Induced Visual Invariances0
Scratch that! An Evolution-based Adversarial Attack against Neural NetworksCode0
Efficient feature embedding of 3D brain MRI images for content-based image retrieval with deep metric learning0
Towards Robust Image Classification Using Sequential Attention Models0
Domain-independent Dominance of Adaptive MethodsCode0
An Automated Deep Learning Approach for Bacterial Image Classification0
On the Validity of Bayesian Neural Networks for Uncertainty Estimation0
Less Is Better: Unweighted Data Subsampling via Influence FunctionCode0
Google street view and deep learning: a new ground truthing approach for crop mapping0
Learning scale-variant features for robust iris authentication with deep learning based ensemble framework0
AP-Perf: Incorporating Generic Performance Metrics in Differentiable LearningCode0
STAR-Caps: Capsule Networks with Straight-Through Attentive Routing0
ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models0
Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection0
Discriminative Joint Probability Maximum Mean Discrepancy (DJP-MMD) for Domain AdaptationCode0
L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise0
Data Parameters: A New Family of Parameters for Learning a Differentiable CurriculumCode0
DATA: Differentiable ArchiTecture ApproximationCode0
Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks0
Gaussian-Based Pooling for Convolutional Neural NetworksCode0
Constrained deep neural network architecture search for IoT devices accounting for hardware calibration0
SGAS: Sequential Greedy Architecture SearchCode0
Show:102550
← PrevPage 325 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
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