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 96519675 of 10420 papers

TitleStatusHype
Comb, Prune, Distill: Towards Unified Pruning for Vision Model CompressionCode0
NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional VisualizationsCode0
Neuro-Inspired Deep Neural Networks with Sparse, Strong ActivationsCode0
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed TrainingCode0
Deep Gradient Compression Reduce the Communication Bandwidth For distributed TraningCode0
Learning by Self-ExplainingCode0
Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning ServicesCode0
1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification TrackCode0
Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray ImagesCode0
Learning Compressed Transforms with Low Displacement RankCode0
DeepFool: a simple and accurate method to fool deep neural networksCode0
Deep Sparse Representation-based ClassificationCode0
Test Sample Accuracy Scales with Training Sample Density in Neural NetworksCode0
Improving Deep Learning Optimization through Constrained Parameter RegularizationCode0
Adversarial Structure Matching for Structured Prediction TasksCode0
Unrestricted Adversarial Examples via Semantic ManipulationCode0
Learning Convolutional Neural Networks using Hybrid Orthogonal Projection and EstimationCode0
Biased Importance Sampling for Deep Neural Network TrainingCode0
Deep Feature Response Discriminative CalibrationCode0
NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep LearningCode0
Learning Curves for Analysis of Deep NetworksCode0
Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge EnsemblesCode0
Multi-scale Processing of Noisy Images using Edge Preservation LossesCode0
Deep Ensembling of Multiband Images for Earth Remote Sensing and Foramnifera DataCode0
Predicting Yelp Star Reviews Based on Network Structure with Deep LearningCode0
Show:102550
← PrevPage 387 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
10RevCol-HTop 1 Accuracy90Unverified