Objects365
PulseAugur coverage of Objects365 — every cluster mentioning Objects365 across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
EdgeCrafter: Compact ViTs for Edge Dense Prediction
Researchers have developed EdgeCrafter, a new framework utilizing compact Vision Transformers (ViTs) designed for dense prediction tasks on edge devices. This framework addresses the challenge of deploying high-performa…
-
New framework enhances visual grounding models with diverse representations
Researchers have developed a new framework to improve visual grounding models by addressing representation degeneration. The proposed method, which includes a Modulated Attention-Contrastive Head (mACH) and a text-condi…
-
ExDet framework boosts open-domain object detection generalization
Researchers have introduced ExDet, a novel framework designed to improve open-domain open-vocabulary detection (ODOVD) capabilities. This lightweight system enhances the generalization of existing detectors to new categ…
-
LVLMs can self-improve small object grounding using attention patterns
Researchers have developed a novel framework, ACS-Learned, that leverages the internal attention patterns of Large Vision Language Models (LVLMs) to improve the grounding of small objects without requiring fine-tuning. …
-
TinyFormer hybrid detector improves small object detection accuracy
Researchers have introduced TinyFormer, a novel hybrid object detection model designed to improve the identification of small objects. This model combines elements of YOLO and DETR architectures, incorporating Vision Tr…