SOTAVerified

Object Categorization

Object categorization identifies which label, from a given set, best corresponds to an image region defined by an input image and bounding box.

Papers

Showing 1120 of 80 papers

TitleStatusHype
Deep Learning Human Mind for Automated Visual ClassificationCode0
Are we done with object recognition? The iCub robot's perspectiveCode0
Cost-Effective Active Learning for Deep Image ClassificationCode0
Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNsCode0
Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN ModelsCode0
Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorizationCode0
Data augmentation instead of explicit regularizationCode0
Collaborative Receptive Field LearningCode0
Learning robust visual representations using data augmentation invarianceCode0
Systematic evaluation of CNN advances on the ImageNetCode0
Show:102550
← PrevPage 2 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Unified-IOXLCategorization (ablation)61.7Unverified
2GPV-2Categorization (ablation)54.7Unverified
3CLIPCategorization (ablation)48.1Unverified
4OFA_LargeCategorization (ablation)22.6Unverified