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 43014325 of 10420 papers

TitleStatusHype
FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural NetworksCode0
Continual and Multi-Task Architecture SearchCode0
How Flawed Is ECE? An Analysis via Logit SmoothingCode0
Associative Alignment for Few-shot Image ClassificationCode0
Context-Gated ConvolutionCode0
Continual Contrastive Learning for Image ClassificationCode0
HOLMES: HOLonym-MEronym based Semantic inspection for Convolutional Image ClassifiersCode0
From Xception to NEXcepTion: New Design Decisions and Neural Architecture SearchCode0
FR-CapsNet: Enhancing Low-Resolution Image Classification via Frequency Routed CapsulesCode0
Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak LabelsCode0
FRAIN to Train: A Fast-and-Reliable Solution for Decentralized Federated LearningCode0
Hyperspectral Image Classification: Artifacts of Dimension Reduction on Hybrid CNNCode0
Histopathological Image Classification using Discriminative Feature-oriented Dictionary LearningCode0
Homogeneous Learning: Self-Attention Decentralized Deep LearningCode0
Hyperspectral Image Classification via Sparse Representation With Incremental DictionariesCode0
FragFake: A Dataset for Fine-Grained Detection of Edited Images with Vision Language ModelsCode0
ISLE: An Intelligent Streaming Framework for High-Throughput AI Inference in Medical ImagingCode0
Fractional Max-PoolingCode0
FractalNet: Ultra-Deep Neural Networks without ResidualsCode0
Assisted Perception: Optimizing Observations to Communicate StateCode0
Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networksCode0
Fully Convolutional Architectures for Multi-Class Segmentation in Chest RadiographsCode0
Continual Learning in Open-vocabulary Classification with Complementary Memory SystemsCode0
Cartoon Face Recognition: A Benchmark DatasetCode0
Context-Aware Compilation of DNN Training Pipelines across Edge and CloudCode0
Show:102550
← PrevPage 173 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