Tag: Transfer Learning
-
SAM Zero-Shot Medical Segmentation: 14% mIoU vs CNN 68%
Compare SAM zero-shot medical segmentation achieving just 14% mIoU against CNN's 68%. Discover why domain shift breaks foundation models.
-
ViT Overfits Small Datasets: When CNNs Win by 18% mAP
Vision Transformers struggle on small datasets while CNNs dominate. Learn why architectural inductive bias beats attention when data is scarce.
-
Transfer Learning CWRU to Custom Bearings: 89% to 67% Drop Fix
Transfer learning CWRU bearings to custom hardware hits 67% accuracy? Learn the domain gap fix with synthetic data and fine-tuning strategies.
-
RL Transfer Learning: Atari to Custom Tasks with SB3
Transfer a pretrained DQN from Atari Pong to custom tasks in 100 episodes. Replay buffer tricks and exploration tuning that actually work.
-
Part 6: Beyond Simulation: Addressing the Sim-to-Real Gap
Bridge the sim-to-real gap: domain randomization cut our robot failure rate by 73%. Here's the exact transfer learning pipeline we used.
-
Transfer Learning์ผ๋ก ์๋ ๋ฐ์ดํฐ ๊ณ ์ฅ ์ง๋จ ๊ตฌํ
Transfer Learning on 50 images: fine-tune ImageNet CNNs for 94% fault detection accuracy. Beats training from scratch with 1000+ samples.