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 76017625 of 10420 papers

TitleStatusHype
Maximum Entropy Regularization and Chinese Text Recognition0
Learning to Reweight with Deep Interactions0
StyPath: Style-Transfer Data Augmentation For Robust Histology Image ClassificationCode0
AUSN: Approximately Uniform Quantization by Adaptively Superimposing Non-uniform Distribution for Deep Neural Networks0
Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning0
Classification with 2-D Convolutional Neural Networks for breast cancer diagnosisCode0
C2G-Net: Exploiting Morphological Properties for Image Classification0
Deep Reinforcement Learning and its Neuroscientific Implications0
Learning the Prediction Distribution for Semi-Supervised Learning with Normalising FlowsCode0
Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches0
Bespoke vs. Prêt-à-Porter Lottery Tickets: Exploiting Mask Similarity for Trainable Sub-Network Finding0
Deep Learning for Apple Diseases: Classification and Identification0
Weakly Supervised Domain Adaptation for Built-up Region Segmentation in Aerial and Satellite ImageryCode0
On Connections between Regularizations for Improving DNN Robustness0
CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge0
Towards Robust Deep Learning with Ensemble Networks and Noisy Layers0
Self-supervised Neural Architecture Search0
Interactive Knowledge Distillation0
Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring0
Selecting Regions of Interest in Large Multi-Scale Images for Cancer Pathology0
Self-Supervised GAN CompressionCode0
Surrogate-assisted Particle Swarm Optimisation for Evolving Variable-length Transferable Blocks for Image Classification0
Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?Code0
Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture0
A Novel BGCapsule Network for Text Classification0
Show:102550
← PrevPage 305 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