Pith. sign in

REVIEW 2 cited by

CrossKD: Cross-Head Knowledge Distillation for 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

arxiv 2306.11369 v2 pith:4HT2HYIJ submitted 2023-06-20 cs.CV

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

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this paper, we present a general and effective prediction mimicking distillation scheme, called CrossKD, which delivers the intermediate features of the student's detection head to the teacher's detection head. The resulting cross-head predictions are then forced to mimic the teacher's predictions. This manner relieves the student's head from receiving contradictory supervision signals from the annotations and the teacher's predictions, greatly improving the student's detection performance. Moreover, as mimicking the teacher's predictions is the target of KD, CrossKD offers more task-oriented information in contrast with feature imitation. On MS COCO, with only prediction mimicking losses applied, our CrossKD boosts the average precision of GFL ResNet-50 with 1x training schedule from 40.2 to 43.7, outperforming all existing KD methods. In addition, our method also works well when distilling detectors with heterogeneous backbones. Code is available at https://github.com/jbwang1997/CrossKD.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks

    cs.LG 2025-08 conditional novelty 5.0 of 10

    HKT is a modular feature-level distillation method whose genetic attention residual improves compact vision models on optical flow, classification, and segmentation benchmarks.

  2. Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition

    cs.LG 2025-05 conditional novelty 4.0 of 10

    PatchEchoClassifier combines an echo state network with DeiT-style distillation from an MLP-Mixer teacher to reach about 86% accuracy on SHL human activity data at much lower FLOPs, though it falls below 80% on four o...

Pith tools