A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
Trash- can: A semantically-segmented dataset towards visual de- tection of marine debris
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
This paper presents TrashCan, a large dataset comprised of images of underwater trash collected from a variety of sources, annotated both using bounding boxes and segmentation labels, for development of robust detectors of marine debris. The dataset has two versions, TrashCan-Material and TrashCan-Instance, corresponding to different object class configurations. The eventual goal is to develop efficient and accurate trash detection methods suitable for onboard robot deployment. Along with information about the construction and sourcing of the TrashCan dataset, we present initial results of instance segmentation from Mask R-CNN and object detection from Faster R-CNN. These do not represent the best possible detection results but provides an initial baseline for future work in instance segmentation and object detection on the TrashCan dataset.
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 4roles
dataset 1polarities
use dataset 1representative citing papers
DC-TTA improves interactive segmentation accuracy by partitioning user clicks into subsets for independent test-time adaptation of SAM models and merging the specialized predictors.
A promptable model trained on 1B masks achieves competitive zero-shot segmentation performance across tasks and is released publicly with its dataset.
SAM 2 delivers more accurate video segmentation with 3x fewer user interactions and 6x faster image segmentation than the original SAM by training a streaming-memory transformer on the largest video segmentation dataset collected to date.
citing papers explorer
-
Vision as Unified Multimodal Generation
A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
-
DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation
DC-TTA improves interactive segmentation accuracy by partitioning user clicks into subsets for independent test-time adaptation of SAM models and merging the specialized predictors.
-
Segment Anything
A promptable model trained on 1B masks achieves competitive zero-shot segmentation performance across tasks and is released publicly with its dataset.
-
SAM 2: Segment Anything in Images and Videos
SAM 2 delivers more accurate video segmentation with 3x fewer user interactions and 6x faster image segmentation than the original SAM by training a streaming-memory transformer on the largest video segmentation dataset collected to date.