[KongchangAI]
Unverified50% confidenceOpinionExact time

If the depth and segmentation branches participate in the forward pass during training and are suddenly removed at inference, the gradient distribution the encoder receives changes, and some feature channels that depend on the auxiliary paths may become 'idle,' wasting representational capacity.

1
Sources
50%
Confidence
Long-term
Relevance
11/8/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1147512
API
curl https://kongchang.com/api/v1/knowledge/claims/1147512
MCP
get_claim(id=1147512)