We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The crux of knowledge distillation is to effectively train a resource-limited student model with the guide of a pre-trained larger teacher model. However, when there is a large difference between the model complexities of teacher and student (i.e., capacity gap), knowledge distillation loses its strength in transferring knowledge from the teacher to the student, thus training a weaker student. To mitigate the impact of the capacity gap, we introduce knowledge distillation via intermediate heads. By extending the intermediate layers of the teacher (at various depths) with classifier heads, we cheaply acquire a cohort of heterogeneous pre-trained teachers. The intermediate classifier heads can all together be efficiently learned while freezing the backbone of the pre-trained teacher. The cohort of teachers (including the original teacher) co-teach the student simultaneously. Our experiments on various teacher-student pairs and datasets have demonstrated that the proposed approach outperforms the canonical knowledge distillation approach and its extensions.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.00497")
get_code_for_paper("2103.00497")
have("2103.00497")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.00497.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.00497)
Connect an agent — have() is free.