Pith. sign in

REVIEW 1 cited by

Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition

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 2209.14498 v1 pith:FAXVCBGY submitted 2022-09-29 cs.CV

classification cs.CV
keywords attentionknowledgenetworkrecognitiondistillationfaceperformanceresolution
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention similarity knowledge distillation approach, which transfers attention maps obtained from a high resolution (HR) network as a teacher into an LR network as a student to boost LR recognition performance. Inspired by humans being able to approximate an object's region from an LR image based on prior knowledge obtained from HR images, we designed the knowledge distillation loss using the cosine similarity to make the student network's attention resemble the teacher network's attention. Experiments on various LR face related benchmarks confirmed the proposed method generally improved recognition performances on LR settings, outperforming state-of-the-art results by simply transferring well-constructed attention maps. The code and pretrained models are publicly available in the https://github.com/gist-ailab/teaching-where-to-look.

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. Knowledge Distillation in RNN-Attention Models for Early Prediction of Student Performance

    cs.LG 2024-12 conditional novelty 4.0 of 10

    An RNN-attention model with knowledge distillation predicts at-risk students slightly better than standard RNNs using only early course weeks, on four years of one university course.

Pith tools