COCO-Stuff
PulseAugur coverage of COCO-Stuff — every cluster mentioning COCO-Stuff across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New 'Hide and Seek' method explains black-box vision models without weights
Researchers have developed a new method called Hide and Seek (HnS) for interpreting black-box vision models. Unlike previous methods, HnS does not require access to model weights or concept-annotated datasets. It works …
-
New research explores uncertainty quantification and lightweight models for semantic segmentation
Researchers are exploring methods to improve the reliability and robustness of semantic segmentation models, particularly for safety-critical applications. One paper investigates the integration of uncertainty quantific…
-
New Bootleg method enhances self-supervised learning for AI models
Researchers have developed a new self-supervised learning method called Bootleg, which aims to combine the stability of generative approaches with the efficiency of predictive methods. Bootleg trains a model to predict …
-
New D3S2 method distills datasets for semantic segmentation
Researchers have developed D3S2, a novel framework for dataset distillation specifically designed for semantic segmentation tasks. This method addresses challenges like class imbalance and the need for precise pixel ali…
-
DINOv3 powers new open-vocabulary semantic segmentation for remote sensing imagery
Researchers have developed CAFe-DINO, a new model for open-vocabulary semantic segmentation of remote sensing imagery. This model leverages the DINOv3 backbone, which has demonstrated strong performance on segmentation …