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 751775 of 10419 papers

TitleStatusHype
A Closer Look at Self-Supervised Lightweight Vision TransformersCode1
BionoiNet: ligand-binding site classification with off-the-shelf deep neural networkCode1
Addressing Failure Detection by Learning Model ConfidenceCode1
High-parallelism Inception-like Spiking Neural Networks for Unsupervised Feature LearningCode1
Addressing Failure Prediction by Learning Model ConfidenceCode1
Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive LearningCode1
Understanding the Role of the Projector in Knowledge DistillationCode1
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of EnsemblesCode1
An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic ProcessorCode1
Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image ClassificationCode1
Black-box Few-shot Knowledge DistillationCode1
Denoised Smoothing: A Provable Defense for Pretrained ClassifiersCode1
Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box AttacksCode1
Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal InformationCode1
An Empirical Investigation of Representation Learning for ImitationCode1
An Empirical Investigation of the Role of Pre-training in Lifelong LearningCode1
Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz NetworksCode1
Augmentation Strategies for Learning with Noisy LabelsCode1
A deep active learning system for species identification and counting in camera trap imagesCode1
Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected BuildingsCode1
Boosting the Adversarial Transferability of Surrogate Models with Dark KnowledgeCode1
Deep Fast Vision: Accelerated Deep Transfer Learning Vision Prototyping and BeyondCode1
All you need is a good initCode1
Boosting Multi-Label Image Classification with Complementary Parallel Self-DistillationCode1
Deep convolutional tensor networkCode1
Show:102550
← PrevPage 31 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
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