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 951–975 of 2042 papers

TitleStatusHype
Image Description using Visual Dependency Representations—0
Image Enhancement and Object Recognition for Night Vision Surveillance—0
IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report—0
Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning—0
ImageNet MPEG-7 Visual Descriptors - Technical Report—0
BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning—0
Disaggregated Deep Learning via In-Physics Computing at Radio Frequency—0
Image Optimization and Prediction—0
BORDER: An Oriented Rectangles Approach to Texture-Less Object Recognition—0
An Efficient Edge Detection Approach to Provide Better Edge Connectivity for Image Analysis—0
Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition—0
Amodal Completion and Size Constancy in Natural Scenes—0
Imaging-free object recognition enabled by optical coherence—0
Immersive Language Exploration with Object Recognition and Augmented Reality—0
Direct Object Recognition Without Line-of-Sight Using Optical Coherence—0
I-MPN: Inductive Message Passing Network for Efficient Human-in-the-Loop Annotation of Mobile Eye Tracking Data—0
Boosting with Maximum Adaptive Sampling—0
Improved Deep Metric Learning with Multi-class N-pair Loss Objective—0
Improved Few-Shot Visual Classification—0
Improved Inception-Residual Convolutional Neural Network for Object Recognition—0
Improved training of binary networks for human pose estimation and image recognition—0
Improved visible to IR image transformation using synthetic data augmentation with cycle-consistent adversarial networks—0
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data—0
Automatically Discovering Local Visual Material Attributes—0
An Efficient Accelerator Design Methodology for Deformable Convolutional Networks—0
Show:102550
← PrevPage 39 of 82Next →
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