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 75517575 of 10420 papers

TitleStatusHype
Verification of Deep Convolutional Neural Networks Using ImageStarsCode1
DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution EnvironmentsCode1
Understanding the decisions of CNNs: An in-model approachCode1
Detached Error Feedback for Distributed SGD with Random Sparsification0
Multimodal Categorization of Crisis Events in Social MediaCode1
Improved Residual Networks for Image and Video RecognitionCode1
Exploring Optimal Deep Learning Models for Image-based Malware Variant Classification0
ASL Recognition with Metric-Learning based Lightweight Network0
X3D: Expanding Architectures for Efficient Video RecognitionCode2
Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training0
TensorProjection Layer: A Tensor-Based Dimension Reduction Method in Deep Neural NetworksCode0
Towards Reusable Network Components by Learning Compatible Representations0
Empirical Perspectives on One-Shot Semi-supervised Learning0
Two-Stage Resampling for Convolutional Neural Network Training in the Imbalanced Colorectal Cancer Image Classification0
Radon cumulative distribution transform subspace modeling for image classificationCode0
Inspector Gadget: A Data Programming-based Labeling System for Industrial Images0
Increasing the Inference and Learning Speed of Tsetlin Machines with Clause Indexing0
Teacher-Class Network: A Neural Network Compression MechanismCode0
Generative Adversarial Zero-shot Learning via Knowledge Graphs0
Evolving Normalization-Activation LayersCode1
Network Adjustment: Channel Search Guided by FLOPs Utilization RatioCode1
Large-scale spatiotemporal photonic reservoir computer for image classification0
Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition0
Comparative Analysis of Multiple Deep CNN Models for Waste Classification0
Approximate Manifold Defense Against Multiple Adversarial PerturbationsCode0
Show:102550
← PrevPage 303 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