REVIEW 3 cited by
GridMask Data Augmentation
Not yet reviewed by Pith; the record is open.
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
read the original abstract
We propose a novel data augmentation method `GridMask' in this paper. It utilizes information removal to achieve state-of-the-art results in a variety of computer vision tasks. We analyze the requirement of information dropping. Then we show limitation of existing information dropping algorithms and propose our structured method, which is simple and yet very effective. It is based on the deletion of regions of the input image. Our extensive experiments show that our method outperforms the latest AutoAugment, which is way more computationally expensive due to the use of reinforcement learning to find the best policies. On the ImageNet dataset for recognition, COCO2017 object detection, and on Cityscapes dataset for semantic segmentation, our method all notably improves performance over baselines. The extensive experiments manifest the effectiveness and generality of the new method.
Forward citations
Cited by 3 Pith papers
-
AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition
On vein-recognition benchmarks, mixup-style augmentations win on clean accuracy but hurt calibration and adversarial robustness, while simple geometric transforms usually hurt performance.
-
Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
Puzzles synthesizes posed video-depth clips from single images and keyframes, letting 3D reconstruction models match full-data accuracy using only 10% of the data.
-
DoorDet: Semi-Automated Multi-Class Door Detection Dataset via Object Detection and Large Language Models
The abstract and body describe different papers; the body proposes TriReWeight, a re-weighting wrapper for generative data augmentation claimed to add 2.9 to 7.9 accuracy points in small-dataset classification.
Discussion (0). Sign in to comment.