SOTAVerified

Object Recognition

Object recognition is a computer vision technique for detecting + classifying objects in images or videos. Since this is a combined task of object detection plus image classification, the state-of-the-art tables are recorded for each component task here and here.

( Image credit: Tensorflow Object Detection API )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 851–900 of 2042 papers

TitleStatusHype
Classifying Malware Images with Convolutional Neural Network Models—0
All-Weather Object Recognition Using Radar and Infrared Sensing—0
3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations—0
WaveTransform: Crafting Adversarial Examples via Input Decomposition—0
An Overview Of 3D Object Detection—0
Medical Deep Learning -- A systematic Meta-Review—0
Fit to Measure: Reasoning about Sizes for Robust Object RecognitionCode0
Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification—0
Unsupervised Vision-and-Language Pre-training Without Parallel Images and CaptionsCode1
Object-aware Feature Aggregation for Video Object Detection—0
LCD -- Line Clustering and Description for Place RecognitionCode1
Boosting Gradient for White-Box Adversarial Attacks—0
Teacher-Student Consistency For Multi-Source Domain AdaptationCode0
Vision-Based Layout Detection from Scientific Literature using Recurrent Convolutional Neural Networks—0
Unsupervised Foveal Vision Neural Networks with Top-Down Attention—0
Dreaming with ARC—0
On the surprising similarities between supervised and self-supervised models—0
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense GraphsCode1
Exact neural mass model for synaptic-based working memory—0
Development of Open Informal Dataset Affecting Autonomous Driving—0
Text-Embedded Bilinear Model for Fine-Grained Visual Recognition—0
The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like DomainCode1
Spherical Convolutional Neural Networks: Stability to Perturbations in SO(3)—0
Quantifying Adversarial Sensitivity of a Model as a Function of the Image Distribution—0
Brain-Like Object Recognition Neural Networks are more robustness to common corruptions—0
How does task structure shape representations in deep neural networks?—0
Deep Feature Collaboration for Challenging 3D Finger Knuckle IdentificationCode0
Explaining Clinical Decision Support Systems in Medical Imaging using Cycle-Consistent Activation Maximization—0
Fast Fourier Transformation for Optimizing Convolutional Neural Networks in Object Recognition—0
Visual Object Recognition in Indoor Environments Using Topologically Persistent FeaturesCode0
Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud—0
Learning to Represent Image and Text with Denotation Graph—0
A Study for Universal Adversarial Attacks on Texture Recognition—0
Evaluating Progress on Machine Learning for Longitudinal Electronic Healthcare Data—0
Transformers: State-of-the-Art Natural Language ProcessingCode0
Robust and Efficient Post-Processing for Video Object Detection (REPP)Code1
Training CNNs in Presence of JPEG Compression: Multimedia Forensics vs Computer Vision—0
Neurocoder: Learning General-Purpose Computation Using Stored Neural Programs—0
Robust and efficient post-processing for video object detectionCode1
Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation—0
PennSyn2Real: Training Object Recognition Models without Human Labeling—0
Angular Luminance for Material Segmentation—0
Open-Ended Fine-Grained 3D Object Categorization by Combining Shape and Texture Features in Multiple Colorspaces—0
3D_DEN: Open-ended 3D Object Recognition using Dynamically Expandable NetworksCode0
A Multisensory Learning Architecture for Rotation-invariant Object Recognition—0
Object Recognition for Economic Development from Daytime Satellite Imagery—0
Performance of object recognition in wearable videos—0
SWP-LeafNET: A novel multistage approach for plant leaf identification based on deep CNN—0
Binarized Neural Architecture Search for Efficient Object Recognition—0
A Review on Near Duplicate Detection of Images using Computer Vision Techniques—0
Show:102550
← PrevPage 18 of 41Next →
All datasetsshape biasCIFAR10-DVSN-Caltech 101ObjectNet (All classes)ObjectNet (ImageNet classes)ObjectNet (ImageNet classes, trained on ImageNet)DVS128 GestureMECCANON-CARS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Imagenshape bias98.7—Unverified
2Stable Diffusionshape bias92.7—Unverified
3Partishape bias91.7—Unverified
4ViT-22B-384shape bias86.4—Unverified
5ViT-22B-560shape bias83.8—Unverified
6CLIP (ViT-B)shape bias79.9—Unverified
7ViT-22B-224shape bias78—Unverified
8ResNet-50 (L2 eps 5.0 adv trained)shape bias69.5—Unverified
9ResNet-50 (with strong augmentations)shape bias62.2—Unverified
10SWSL (ResNeXt-101)shape bias49.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.55—Unverified
2SSNNAccuracy (% )78.57—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.62—Unverified
2SSNNAccuracy (% )79.25—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy18.75—Unverified
2yunTop 5 Accuracy14.75—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24—Unverified
2DYTop 5 Accuracy0.08—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24—Unverified
2AJ2021Top 5 Accuracy27.68—Unverified
#ModelMetricClaimedVerifiedStatus
1SSNNAccuracy (% )94.91—Unverified
#ModelMetricClaimedVerifiedStatus
1Faster-RCNNmAP30.39—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )96—Unverified