Pith. sign in

REVIEW 1 cited by

PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization

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

arxiv 2211.06560 v3 pith:UVA4IMWC submitted 2022-11-12 cs.CV

classification cs.CV
keywords segmentationlogitmodelsbasebiasesbinaryconsistentlyfalse
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

The purpose of binary segmentation models is to determine which pixels belong to an object of interest (e.g., which pixels in an image are part of roads). The models assign a logit score (i.e., probability) to each pixel and these are converted into predictions by thresholding (i.e., each pixel with logit score $\geq \tau$ is predicted to be part of a road). However, a common phenomenon in current and former state-of-the-art segmentation models is spatial bias -- in some patches, the logit scores are consistently biased upwards and in others they are consistently biased downwards. These biases cause false positives and false negatives in the final predictions. In this paper, we propose PatchRefineNet (PRN), a small network that sits on top of a base segmentation model and learns to correct its patch-specific biases. Across a wide variety of base models, PRN consistently helps them improve mIoU by 2-3\%. One of the key ideas behind PRN is the addition of a novel supervision signal during training. Given the logit scores produced by the base segmentation model, each pixel is given a pseudo-label that is obtained by optimally thresholding the logit scores in each image patch. Incorporating these pseudo-labels into the loss function of PRN helps correct systematic biases and reduce false positives/negatives. Although we mainly focus on binary segmentation, we also show how PRN can be extended to saliency detection and few-shot segmentation. We also discuss how the ideas can be extended to multiclass segmentation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. SAMIC: Segment Anything with In-Context Spatial Prompt Engineering

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A 2.6-million-parameter learned prompt generator for SAM achieves state-of-the-art or competitive one-shot segmentation on multiple benchmarks using only 20% of the training data.

Pith tools