Pith. sign in

REVIEW 6 cited by

TACO: Trash Annotations in Context for Litter Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2003.06975 v2 pith:EXUFQ5KC submitted 2020-03-16 cs.CV

Pedro F Proença , Pedro Simões This is my paper
classification cs.CV
keywords tacoannotationsdetectiondatasetlittersegmentationtrashachieve
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

TACO is an open image dataset for litter detection and segmentation, which is growing through crowdsourcing. Firstly, this paper describes this dataset and the tools developed to support it. Secondly, we report instance segmentation performance using Mask R-CNN on the current version of TACO. Despite its small size (1500 images and 4784 annotations), our results are promising on this challenging problem. However, to achieve satisfactory trash detection in the wild for deployment, TACO still needs much more manual annotations. These can be contributed using: http://tacodataset.org/

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MDWD: A Street-Level Dataset for Municipal Solid Waste Detection in Dense Urban Environments

    cs.CV 2026-07 conditional novelty 6.0 of 10

    MDWD is a new instance-level street waste benchmark; RF-DETR-M tops it at 94.49% mAP50, showing off-the-shelf detectors train well on municipal waste imagery.

  2. WS$^2$: Weakly Supervised Segmentation using Before-After Supervision in Waste Sorting

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Before-after supervision from human removal actions can train a segmentation model for unwanted-object detection in waste sorting, and the authors release an 11,060-frame dataset to benchmark this setting.

  3. Synthetic and Derived Training Images for Campus Waste Detection: A Multi-Seed Evaluation with YOLOv8n

    cs.CV 2026-07 accept novelty 5.0 of 10

    Adding 695 synthetic or derived training images did not improve a YOLOv8n campus-waste detector over the real-only baseline; image source mattered more than image count.

  4. Robust and Label-Efficient Deep Waste Detection

    cs.CV 2025-08 conditional novelty 5.0 of 10

    An ensemble-based soft pseudo-labeling pipeline improves waste detection on the ZeroWaste dataset, beating fully supervised training with the same labeled images.

  5. A Roadmap for Climate-Relevant Robotics Research

    cs.RO 2025-07 unverdicted novelty 5.0 of 10

    A collaborative roadmap identifies high-impact opportunities for robotics research in six climate domains, aimed at inspiring new interdisciplinary work.

  6. YOLO-SAT: A Data-based and Model-based Enhanced YOLOv12 Model for Desert Waste Detection and Classification

    cs.CV 2025-11 conditional novelty 3.0 of 10

    A pruned YOLOv12n with augmentation and self-adversarial training reports 94% mAP@0.5 and 4.67 MB size on the DroneTrashNet desert-litter dataset, claiming real-time deployment.

Pith tools