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 1010110125 of 10420 papers

TitleStatusHype
Data-dependent Initializations of Convolutional Neural NetworksCode0
Top-k Multiclass SVMCode0
Semantic Diversity versus Visual Diversity in Visual Dictionaries0
Training CNNs with Low-Rank Filters for Efficient Image Classification0
How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?0
Convolutional Clustering for Unsupervised Learning0
All you need is a good initCode1
Geodesics of learned representations0
Compact Bilinear PoolingCode0
Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial NetworksCode0
Learning to Generate Images with Perceptual Similarity Metrics0
Competitive Multi-scale Convolution0
Sparse learning of maximum likelihood model for optimization of complex loss function0
Staleness-aware Async-SGD for Distributed Deep LearningCode0
Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learning0
Learning Structured Inference Neural Networks with Label Relations0
DeepFool: a simple and accurate method to fool deep neural networksCode0
Learning Fine-grained Features via a CNN Tree for Large-scale Classification0
Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning0
Universum Prescription: Regularization using Unlabeled Data0
Tiny Descriptors for Image Retrieval with Unsupervised Triplet Hashing0
The Radon cumulative distribution transform and its application to image classification0
Batch-normalized Maxout Network in NetworkCode0
Pooling the Convolutional Layers in Deep ConvNets for Action Recognition0
Image classification based on support vector machine and the fusion of complementary features0
Show:102550
← PrevPage 405 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