SOTAVerified

Object Detection

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4301–4350 of 10957 papers

TitleStatusHype
Towards Universal LiDAR-Based 3D Object Detection by Multi-Domain Knowledge Transfer—0
PODA: Prompt-driven Zero-shot Domain AdaptationCode1
Building Vision Transformers with Hierarchy Aware Feature Aggregation—0
Improving CLIP Fine-tuning PerformanceCode2
Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's-Eye ViewCode1
LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding—0
Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object DetectionCode1
BiViT: Extremely Compressed Binary Vision Transformers—0
Bidirectional Alignment for Domain Adaptive Detection with TransformersCode0
DETR Does Not Need Multi-Scale or Locality DesignCode2
MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation—0
Novel Scenes & Classes: Towards Adaptive Open-set Object DetectionCode1
s-Adaptive Decoupled Prototype for Few-Shot Object Detection—0
Open-Vocabulary Object Detection With an Open Corpus—0
AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts—0
XiNet: Efficient Neural Networks for tinyML—0
Deep Feature Deblurring Diffusion for Detecting Out-of-Distribution ObjectsCode0
Alleviating Catastrophic Forgetting of Incremental Object Detection via Within-Class and Between-Class Knowledge Distillation—0
Automated Knowledge Distillation via Monte Carlo Tree SearchCode0
Attention Discriminant Sampling for Point Clouds—0
CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection—0
3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object DetectionCode1
Masked Autoencoders Are Stronger Knowledge Distillers—0
LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer NormalizationCode1
A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection—0
Learning from Noisy Data for Semi-Supervised 3D Object DetectionCode1
Self-Supervised Object Detection from Egocentric Videos—0
Semantic Information in Contrastive LearningCode0
ObjectFusion: Multi-modal 3D Object Detection with Object-Centric Fusion—0
Vision HGNN: An Image is More than a Graph of NodesCode1
FocalFormer3D: Focusing on Hard Instance for 3D Object DetectionCode2
AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via TransformersCode0
Generalized UAV Object Detection via Frequency Domain Disentanglement—0
LSTFE-Net:Long Short-Term Feature Enhancement Network for Video Small Object DetectionCode1
IS-GGT: Iterative Scene Graph Generation With Generative Transformers—0
X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection—0
Weak-Shot Object Detection Through Mutual Knowledge Transfer—0
Implicit Surface Contrastive Clustering for LiDAR Point Clouds—0
Discriminating Known From Unknown Objects via Structure-Enhanced Recurrent Variational AutoEncoderCode0
1% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions—0
Semi-Supervised Stereo-Based 3D Object Detection via Cross-View Consensus—0
MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object DetectionCode1
Azimuth Super-Resolution for FMCW Radar in Autonomous DrivingCode1
Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU SupervisionCode1
ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector—0
RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training—0
Co-Salient Object Detection With Uncertainty-Aware Group Exchange-Masking—0
Seeing With Sound: Long-range Acoustic Beamforming for Multimodal Scene Understanding—0
UTM: A Unified Multiple Object Tracking Model With Identity-Aware Feature Enhancement—0
Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic SpaceCode1
Show:102550
← PrevPage 87 of 220Next →
All datasetsCOCO test-devCOCO minivalCOCO-OCOCO 2017 valPASCAL VOC 2007COCO 2017CrowdHuman (full body)CPPE-5LVIS v1.0 valManga109-s 15testPKU-DDD17-CarWaymo 2D detection all_ns f0val

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Co-DETRbox mAP66—Unverified
2InternImage-H (M3I Pre-training)box mAP65.5—Unverified
3M3I Pre-training (InternImage-H)box mAP65.4—Unverified
4MoCaEbox mAP65.1—Unverified
5Co-DETR (Swin-L)box mAP64.8—Unverified
6Focal-Stable-DINO (Focal-Huge, no TTA)box mAP64.8—Unverified
7EVAbox mAP64.7—Unverified
8Group DETR v2box mAP64.5—Unverified
9FocalNet-H (DINO)box mAP64.4—Unverified
10InternImage-XLbox mAP64.3—Unverified