Unverified50% confidenceBenchmarkExact time
Without fine-tuning on real data, the localization head trained on synthetic data improved HOTA for MOTIP and HAT on real video by 0.96 to 1.14.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor image data, the commonly used ImageNet pre-training mean [0.485, 0.456, 0.406] and standard deviation [0.229, 0.224, 0.225] have become the de facto standard.62% similarUnverifiedExtracting state data from game memory (such as boss coordinates, health points, and animation frame numbers) rather than using raw pixel input can improve training efficiency by one to two orders of magnitude.62% similarUnverifiedVersion number increases in models are usually accompanied by optimization directions such as higher native input resolution, dynamic resolution processing, and stronger visual grounding training data.61% similarUnverifiedSynthetic pre-training followed by fine-tuning on a small amount of real data is currently the most practical Sim-to-Real transfer paradigm.60% similarUnverifiedThe pretraining and fine-tuning paradigm originated from NLP and computer vision, with its core being large-scale data pretraining to learn general low-level features, and downstream tasks adapted using a small amount of labeled data.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/986886API
curl https://kongchang.com/api/v1/knowledge/claims/986886MCP
get_claim(id=986886)