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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 80 papers

TitleStatusHype
Roboflow 100: A Rich, Multi-Domain Object Detection BenchmarkCode2
Learning Transferable Visual Models From Natural Language SupervisionCode2
GRIT: General Robust Image Task BenchmarkCode1
Learning Physical Graph Representations from Visual ScenesCode1
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise LabellingCode1
Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representationsCode0
Divide and Conquer: Improving Multi-Camera 3D Perception with 2D Semantic-Depth Priors and Input-Dependent Queries—0
Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task—0
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception—0
Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers—0
Show:102550
← PrevPage 1 of 8Next →

Benchmark Results

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