Unverified50% confidenceBenchmarkExact time
During training, the held-out FID dropped from 33.7 to 27.0, FD-DINOv2 dropped from 570 to 218, and detector-based object accuracy improved from 65% to 90%.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn a reproduction experiment training for 40 epochs on CIFAR-10, plain-56 achieved a training accuracy of 84.0% and plain-20 achieved a training accuracy of 95.1%, even though plain-56's parameter count (853,018) is approximately three times that of plain-20 (269,722).73% similarUnverifiedIn the same reproduction experiment, ResNet-20 achieved a test accuracy of 90.4% and ResNet-56 achieved a test accuracy of 91.7%, with training accuracies of 97.4% and 99.0% respectively.72% similarUnverified在标准行人检测数据集（如MOTChallenge）上训练的模型，在俯视视角下的检测精度（mAP）通常下降40%-60%70% similarVerifiedIf the accuracy per step is 95%, after 20 steps the overall accuracy will drop to approximately 36%.70% similarUnverified将FP32权重降至INT8后，典型Transformer模型基准测试分数下降通常不超过1%，推理速度提升2至4倍，内存占用减少75%69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/902320API
curl https://kongchang.com/api/v1/knowledge/claims/902320MCP
get_claim(id=902320)