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 401–450 of 2042 papers

TitleStatusHype
Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection—0
Explainable GeoAI: Can saliency maps help interpret artificial intelligence's learning process? An empirical study on natural feature detectionCode1
Improving Out-of-Distribution Detection with Disentangled Foreground and Background FeaturesCode0
Machine Learning Computer Vision Applications for Spatial AI Object Recognition in Orange County, California—0
Feature representations useful for predicting image memorability—0
Variation of Gender Biases in Visual Recognition Models Before and After Finetuning—0
EvConv: Fast CNN Inference on Event Camera Inputs For High-Speed Robot Perception—0
Toward a Geometric Theory of Manifold Untangling—0
Learning Efficient Coding of Natural Images with Maximum Manifold Capacity RepresentationsCode1
Domain-aware Triplet loss in Domain GeneralizationCode0
DuEqNet: Dual-Equivariance Network in Outdoor 3D Object Detection for Autonomous Driving—0
InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation—0
Deep Learning for Event-based Vision: A Comprehensive Survey and BenchmarksCode1
Towards Local Visual Modeling for Image CaptioningCode1
Scaling Vision Transformers to 22 Billion ParametersCode0
Zero-Knowledge Zero-Shot Learning for Novel Visual Category Discovery—0
Convolutional Neural Networks Trained to Identify Words Provide a Surprisingly Good Account of Visual Form Priming Effects—0
Dynamic Atomic Column Detection in Transmission Electron Microscopy Videos via Ridge Estimation—0
Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object ClassificationCode0
Connecting metrics for shape-texture knowledge in computer vision—0
An Efficient Semi-Automated Scheme for Infrastructure LiDAR Annotation—0
Effective Baselines for Multiple Object Rearrangement Planning in Partially Observable Mapped Environments—0
ODOR: The ICPR2022 ODeuropa Challenge on Olfactory Object Recognition—0
Improving Performance of Object Detection using the Mechanisms of Visual Recognition in Humans—0
A Comprehensive Review of Modern Object Segmentation Approaches—0
Visual Story Generation Based on Emotion and KeywordsCode0
TempSAL -- Uncovering Temporal Information for Deep Saliency PredictionCode1
GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition—0
Deep Learning from Parametrically Generated Virtual Buildings for Real-World Object Recognition—0
Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition—0
Autonomous Manipulation Learning for Similar Deformable Objects via Only One Demonstration—0
MISC210K: A Large-Scale Dataset for Multi-Instance Semantic CorrespondenceCode0
TempSAL - Uncovering Temporal Information for Deep Saliency PredictionCode1
Parsing Objects at a Finer Granularity: A Survey—0
Part-guided Relational Transformers for Fine-grained Visual RecognitionCode1
Brain Cancer Segmentation Using YOLOv5 Deep Neural Network—0
Decision-making and control with diffractive optical networksCode0
Improving Pre-Trained Weights Through Meta-Heuristics Fine-TuningCode0
ColorSense: A Study on Color Vision in Machine Visual Recognition—0
RTMDet: An Empirical Study of Designing Real-Time Object DetectorsCode4
OAMixer: Object-aware Mixing Layer for Vision TransformersCode0
Doubly Right Object Recognition: A Why Prompt for Visual RationalesCode1
A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations—0
Teaching What You Should Teach: A Data-Based Distillation Method—0
State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions—0
Beyond Object Recognition: A New Benchmark towards Object Concept Learning—0
Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural NetworksCode0
PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain GeneralizationCode1
Extreme Image Transformations Affect Humans and Machines Differently—0
Efficient multi-scale representation of visual objects using a biologically plausible spike-latency code and winner-take-all inhibition—0
Show:102550
← PrevPage 9 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