papers | Deep Learning JP - Part 37

Manipulation-Independent Representations(MIR) for Successful Cross Embodiment Visual Imitation

ReDet: A Rotation-equivariant Detector for Aerial Object Detection

GANとエネルギーベースモデル

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

自動運転技術の課題に役立つかもしれない論文3本

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning

Diagnosing Vision-and-Language Navigation: What Really Matters

VideoMix: Rethinking Data Augmentation for Video Classification

LoFTR: Detector-Free Local Feature Matching with Transformers

Free Lunch for Few-shot Learning: Distribution Calibration

37 / 95« 先頭 «...10 20 30...35 363738 39...50 60 70...»最後 »