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 83018325 of 10420 papers

TitleStatusHype
Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification0
Attentive NormalizationCode0
MoGA: Searching Beyond MobileNetV3Code0
Kannada-MNIST: A new handwritten digits dataset for the Kannada languageCode0
Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network ModelsCode0
Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features0
Seeing is Not Believing: Camouflage Attacks on Image Scaling AlgorithmsCode0
Quality Assessment of In-the-Wild VideosCode0
Cartoon Face Recognition: A Benchmark DatasetCode0
Competing Ratio Loss for Discriminative Multi-class Image Classification0
Incremental Learning Techniques for Semantic SegmentationCode1
Grid Saliency for Context Explanations of Semantic SegmentationCode1
Open Set Domain Adaptation for Image and Action RecognitionCode0
Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods0
MoBiNet: A Mobile Binary Network for Image Classification0
Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks0
Forced Spatial Attention for Driver Foot Activity ClassificationCode0
On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting MethodCode0
Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT0
Context-Aware Multipath Networks0
DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients0
A Group-Theoretic Framework for Data AugmentationCode0
MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and ClassificationCode0
Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification0
Trading via Image ClassificationCode0
Show:102550
← PrevPage 333 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified