Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟵𝟱 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗬𝗼𝘂 𝗢𝗻𝗹𝘆 𝗖𝘂𝘁 𝗢𝗻𝗰𝗲: 𝗕𝗼𝗼𝘀𝘁𝗶𝗻𝗴 𝗗𝗮𝘁𝗮 𝗔𝘂𝗴𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗮 𝗦𝗶𝗻𝗴𝗹𝗲 𝗖𝘂𝘁 𝗯𝘆 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗶𝘁𝘆 𝗼𝗳 𝗔𝗱𝗲𝗹𝗮𝗶𝗱𝗲 Follow me for a similar post: Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: 𝗬𝗼𝘂 𝗢𝗻𝗹𝘆 𝗖𝘂𝘁 𝗢𝗻𝗰𝗲: 𝗕𝗼𝗼𝘀𝘁𝗶𝗻𝗴 𝗗𝗮𝘁𝗮 𝗔𝘂𝗴𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗮 𝗦𝗶𝗻𝗴𝗹𝗲 𝗖𝘂𝘁 🔸 This paper is published arxiv2022. 🔸 YOCO cuts one image into two equal pieces, either in the height or the width dimension. The same data augmentations are performed independently within each piece. Augmented pieces are then concatenated together to form one single augmented image. 🔸 YOCO cuts one image into two pieces and performs data augmentations individually within each piece. 🔸 Applying YOCO improves the diversity of the augmentation per sample and encourages neural networks to recognize objects from partial information. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 We present You Only Cut Once (YOCO) for performing data augmentations. YOCO cuts one image into two pieces and performs data augmentations individually within each piece.  🔸 Applying YOCO improves the diversity of the augmentation per sample and encourages neural networks to recognize objects from partial information.  🔸 YOCO enjoys the properties of parameter-free, easy usage, and boosting almost all augmentations for free. Thorough experiments are conducted to evaluate its effectiveness.  🔸 We first demonstrate that YOCO can be seamlessly applied to varying data augmentations, neural network architectures, and brings performance gains on CIFAR and ImageNet classification tasks, sometimes surpassing conventional image-level augmentation by large margins.  🔸 Moreover, we show YOCO benefits contrastive pre-training toward a more powerful representation that can be better transferred to multiple downstream tasks. Finally, we study a number of variants of YOCO and empirically analyze the performance for respective settings.   #computervision #artificialintelligence #technology