https://github.com/tmlabonte/weakly-supervised-DETR
공식 코드Scaling Novel Object Detection with Weakly Supervised Detection Transformers
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Replace the cat with a British Shorthair cat of the breed with bulging yellow eyes
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Scaling Novel Object Detection with Weakly Supervised Detection Transformers
Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors
IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
Zero Shot Context-Based Object Segmentation using SLIP (SAM+CLIP)
Contrastive Grouping with Transformer for Referring Image Segmentation
YCB-LUMA: YCB Object Dataset with Luminance Keying for Object Localization
Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection
Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priors
Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors
UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking
Robustness Enhancement of Object Detection in Advanced Driver Assistance Systems (ADAS)
Toward Improving Robustness of Object Detectors Against Domain Shift
On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
Self-supervised visual learning from interactions with objects
Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking
CoupleNet: Coupling Global Structure with Local Parts for Object Detection
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
Learning to Follow Object-Centric Image Editing Instructions Faithfully
Object as Query: Lifting any 2D Object Detector to 3D Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.