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 651–700 of 2042 papers

TitleStatusHype
Learning Underrepresented Classes from Decentralized Partially Labeled Medical Images—0
Deep Optical Coding Design in Computational Imaging—0
Complementary datasets to COCO for object detectionCode0
Guiding Visual Attention in Deep Convolutional Neural Networks Based on Human Eye Movements—0
RendNet: Unified 2D/3D Recognizer With Latent Space Rendering—0
DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection—0
SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networksCode0
Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial NoisesCode0
Continual-Learning-as-a-Service (CLaaS): On-Demand Efficient Adaptation of Predictive Models—0
A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth—0
Improving Fairness in Large-Scale Object Recognition by CrowdSourced Demographic Information—0
Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks—0
OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation—0
The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networksCode0
Efficient visual object representation using a biologically plausible spike-latency code and winner-take-all inhibition—0
Robust Sensible Adversarial Learning of Deep Neural Networks for Image ClassificationCode0
Topologically Persistent Features-based Object Recognition in Cluttered Indoor Environments—0
Efficient Gesture Recognition for the Assistance of Visually Impaired People using Multi-Head Neural Networks—0
A Computational Acquisition Model for Multimodal Word CategorizationCode0
Embodied vision for learning object representations—0
Robustness of Humans and Machines on Object Recognition with Extreme Image Transformations—0
Utility-Oriented Underwater Image Quality Assessment Based on Transfer Learning—0
Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation—0
Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognition—0
Multitask Network for Joint Object Detection, Semantic Segmentation and Human Pose Estimation in Vehicle Occupancy Monitoring—0
Can domain adaptation make object recognition work for everyone?—0
Label Efficient Regularization and Propagation for Graph Node Classification—0
Sensitivity of sparse codes to image distortions—0
Hybrid Predictive Coding: Inferring, Fast and Slow—0
Exploiting Temporal Relations on Radar Perception for Autonomous Driving—0
Neurosymbolic hybrid approach to driver collision warning—0
Salt Detection Using Segmentation of Seismic Image—0
Visuo-Haptic Object Perception for Robots: An Overview—0
A Real-time Junk Food Recognition System based on Machine Learning—0
Computer vision and machine learning for medical image analysis: recent advances, challenges, and way forward—0
Vision Transformer with Convolutions Architecture Search—0
Grasp Pre-shape Selection by Synthetic Training: Eye-in-hand Shared Control on the Hannes ProsthesisCode0
Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans—0
InsCon:Instance Consistency Feature Representation via Self-Supervised Learning—0
Soft-margin classification of object manifolds—0
FisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition—0
Mixed Evidence for Gestalt Grouping in Deep Neural NetworksCode0
Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition—0
The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods—0
Hybrid Optimized Deep Convolution Neural Network based Learning Model for Object Detection—0
TANDEM: Learning Joint Exploration and Decision Making with Tactile Sensors—0
Building a visual semantics aware object hierarchy—0
Universal adversarial perturbation for remote sensing images—0
Visual Ground Truth Construction as Faceted Classification—0
Survey on Self-supervised Representation Learning Using Image Transformations—0
Show:102550
← PrevPage 14 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