REVIEW 1 cited by
Rediscovering BCE Loss for Uniform Classification
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
This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as a metric to measure the model's performance in uniform classification. Furthermore, begin with a naive loss, we mathematically derive a loss function suitable for the uniform classification, which is the BCE function integrated with a unified bias. We demonstrate the unified threshold could be learned via the bias. The extensive experiments on six classification datasets and three feature extraction models show that, compared to the SoftMax loss, the models trained with the BCE loss not only exhibit higher uniform classification accuracy but also higher sample-wise classification accuracy. In addition, the learned bias from BCE loss is very close to the unified threshold used in the uniform classification. The features extracted by the models trained with BCE loss not only possess uniformity but also demonstrate better intra-class compactness and inter-class distinctiveness, yielding superior performance on open-set tasks such as face recognition.
Forward citations
Cited by 1 Pith paper
-
SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation
SCRWKV is a 1.22M-parameter Vision-RWKV model using Structure-Field Encoder with AMCM and SCIU modules plus CSHF decoder that reports F1 0.8428 and mIoU 0.8512 on TUT crack dataset while claiming to outperform prior SOTA.
Discussion (0). Sign in to comment.