REVIEW 7 cited by
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection
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
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection
read the original abstract
Detecting tiny objects is a very challenging problem since a tiny object only contains a few pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory results on tiny objects due to the lack of appearance information. Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors. To alleviate this, we propose a new evaluation metric using Wasserstein distance for tiny object detection. Specifically, we first model the bounding boxes as 2D Gaussian distributions and then propose a new metric dubbed Normalized Wasserstein Distance (NWD) to compute the similarity between them by their corresponding Gaussian distributions. The proposed NWD metric can be easily embedded into the assignment, non-maximum suppression, and loss function of any anchor-based detector to replace the commonly used IoU metric. We evaluate our metric on a new dataset for tiny object detection (AI-TOD) in which the average object size is much smaller than existing object detection datasets. Extensive experiments show that, when equipped with NWD metric, our approach yields performance that is 6.7 AP points higher than a standard fine-tuning baseline, and 6.0 AP points higher than state-of-the-art competitors. Codes are available at: https://github.com/jwwangchn/NWD.
Forward citations
Cited by 7 Pith papers
-
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
TimeLens2 shows that a compact video MLLM can localize multiple evidence intervals in long videos by training on verified interval labels and a Wasserstein-based time-distance reward.
-
Adaptive Slicing-Assisted Hyper Inference for Enhanced Small Object Detection in High-Resolution Imagery
ASAHI adaptively slices high-res images into 6 or 12 patches, adds slicing-assisted fine-tuning, and uses Cluster-DIoU-NMS to hit 56.8% mAP on VisDrone2019 and 22.7% on xView while running 20-25% faster than fixed sli...
-
TargetFinder: Detecting Widgets from Pixels on Desktop Interfaces
A fine-tuned YOLO pipeline on a new 520-screenshot, 38,000-widget dataset detects desktop GUI widgets from pixels and drives system-wide Bubble Cursor and Semantic Pointing.
-
Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detection
Telescope uses learnable hyperbolic foveation to deliver a 76% relative mAP gain (0.185 to 0.326) for objects beyond 250 meters while keeping overhead low.
-
MSG-Loc: Multi-Label Likelihood-based Semantic Graph Matching for Object-Level Global Localization
Object-level global localization becomes more robust to semantic ambiguity by matching multi-label confidence distributions and propagating neighbor likelihoods across semantic graphs.
-
Physics-Informed Super-Resolution of Atmospheric Data
Adding multi-scale hydrostatic-primitive-equation losses to atmospheric super-resolution models improves reported physical-consistency scores and some reconstruction/event-detection metrics, but the metric and constra...
-
ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing
A new industrial wafer-defect challenge and dataset for cross-scenario instance detection and ordinal severity grading, with leaderboards from 21 finalist teams.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.