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 88518875 of 10420 papers

TitleStatusHype
Hyperspectral Image Classification: Artifacts of Dimension Reduction on Hybrid CNNCode0
Quantum Computing Supported Adversarial Attack-Resilient Autonomous Vehicle Perception Module for Traffic Sign ClassificationCode0
MixFormer: Mixing Features across Windows and DimensionsCode0
MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised RepresentationsCode0
Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging ClassificationCode0
Hyperspectral Image Classification in the Presence of Noisy LabelsCode0
CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural NetworksCode0
Attention Masks Help Adversarial Attacks to Bypass Safety DetectorsCode0
Safety Verification of Deep Neural NetworksCode0
Neural Networks Trained on Natural Scenes Exhibit Gestalt ClosureCode0
Hyperspectral Image Classification via Transformer-based Spectral-Spatial Attention Decoupling and Adaptive GatingCode0
Hyperspectral image classification via a random patches networkCode0
Hyperspectral Image Classification via Sparse Representation With Incremental DictionariesCode0
Compact Global Descriptor for Neural NetworksCode0
Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural NetworkCode0
Compact Bilinear PoolingCode0
Domain-Specific Pre-training Improves Confidence in Whole Slide Image ClassificationCode0
Compact and De-biased Negative Instance Embedding for Multi-Instance Learning on Whole-Slide Image ClassificationCode0
Hyperspectral Image Classification With Contrastive Graph Convolutional NetworkCode0
Combined Depth Space based Architecture Search For Person Re-identificationCode0
PadChannel: Improving CNN Performance through Explicit Padding EncodingCode0
Learning Representations by Maximizing Mutual Information Across ViewsCode0
ColorNet: Investigating the importance of color spaces for image classificationCode0
Deeply-supervised Knowledge SynergyCode0
Mixture of Self-Supervised LearningCode0
Show:102550
← PrevPage 355 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