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 20512100 of 10419 papers

TitleStatusHype
Capsules with Inverted Dot-Product Attention RoutingCode1
Over-the-Air Adversarial Flickering Attacks against Video Recognition NetworksCode1
Invariant Risk Minimization GamesCode1
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image ClassificationCode1
Subspace Capsule NetworkCode1
Efficient Model for Image Classification With Regularization TricksCode1
Optimized spiking neurons classify images with high accuracy through temporal coding with two spikesCode1
Post-Training Piecewise Linear Quantization for Deep Neural NetworksCode1
Spiking Inception Module for Multi-layer Unsupervised Spiking Neural NetworksCode1
CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare RecordsCode1
No Routing Needed Between CapsulesCode1
batchboost: regularization for stabilizing training with resistance to underfitting & overfittingCode1
Gradient Surgery for Multi-Task LearningCode1
Harmonic Convolutional Networks based on Discrete Cosine TransformCode1
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural NetworkCode1
Adapting Grad-CAM for Embedding NetworksCode1
Are These Birds Similar: Learning Branched Networks for Fine-grained RepresentationsCode1
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised LearningCode1
Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual FeaturesCode1
Diagnosing Colorectal Polyps in the Wild with Capsule NetworksCode1
Sparse Weight Activation TrainingCode1
FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning NetworkCode1
Discrimination-aware Network Pruning for Deep Model CompressionCode1
A Neural Dirichlet Process Mixture Model for Task-Free Continual LearningCode1
Automated Relational Meta-learningCode1
Towards Accurate Post-training Network Quantization via Bit-Split and StitchingCode1
Understanding Contrastive Representation Learning through Geometry on the HypersphereCode1
Transductive Zero-Shot Learning for 3D Point Cloud ClassificationCode1
PolSF: PolSAR image dataset on San FranciscoCode1
Image Classification with Deep Learning in the Presence of Noisy Labels: A SurveyCode1
AugMix: A Simple Data Processing Method to Improve Robustness and UncertaintyCode1
Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image ClassificationCode1
High-parallelism Inception-like Spiking Neural Networks for Unsupervised Feature LearningCode1
Addressing Failure Detection by Learning Model ConfidenceCode1
Transform-Invariant Convolutional Neural Networks for Image Classification and SearchCode1
GhostNet: More Features from Cheap OperationsCode1
CSPNet: A New Backbone that can Enhance Learning Capability of CNNCode1
Rigging the Lottery: Making All Tickets WinnersCode1
Universal Adversarial Robustness of Texture and Shape-Biased ModelsCode1
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation AnchoringCode1
Beyond Synthetic Noise: Deep Learning on Controlled Noisy LabelsCode1
General E(2)-Equivariant Steerable CNNsCode1
Self-training with Noisy Student improves ImageNet classificationCode1
Multimodal Model-Agnostic Meta-Learning via Task-Aware ModulationCode1
A deep active learning system for species identification and counting in camera trap imagesCode1
Soft-Label Dataset Distillation and Text Dataset DistillationCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Addressing Failure Prediction by Learning Model ConfidenceCode1
Hidden Trigger Backdoor AttacksCode1
Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional NetworkCode1
Show:102550
← PrevPage 42 of 209Next →

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