Home

Info Title: COCO-GAN: Generation by Parts via Conditional Coordinating Task: Image Generation Author: Chieh Hubert Lin, Chia-Che Chang, Yu-Sheng Chen, Da-Cheng Juan, Wei Wei, Hwann-Tzong Chen Date: Apr. 2019 Arxiv: 1904.00284 Published: ICCV 2019 Highlights Discriminator with auxiliary task for content consistency(latent vecto...

Info Title: InGAN: Capturing and Remapping the “DNA” of a Natural Image Task: Image Genration Author: Assaf Shocher, Shai Bagon, Phillip Isola, Michal Irani Date: Dec. 2018 Arxiv: 1812.00231 Published: ICCV 2019 Abstract Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and...

Info Title: Specifying Object Attributes and Relations in Interactive Scene Generation Task: Image Generation Author: Oron Ashual, Lior Wolf Date: Sep. 2019 Arxiv: 1909.05379 Published: ICCV 2019(Best Paper Award Honorable Mentions) Abstract We introduce a method for the generation of images from an input scene graph. The method...

Info Title: Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis Task: Image Generation Date: Oct. 2019 Arxiv: 1910.06809 Published: NIPS 2019 Abstract Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative advers...

Info Title: PolarMask: Single Shot Instance Segmentation with Polar Representation Task: Instance Segmentation Author: Enze Xie, Peize Sun , Xiaoge Song, Wenhai Wang, Xuebo Liu, Ding Liang, Chunhua Shen, Ping Luo Date: Sep. 2019 Published: CVPR 2020(Oral) Arxiv: 1909.13226 Highlights Simple: An...

Info Title: CondConv: Conditionally Parameterized Convolutions for Efficient Inference Author: Brandon Yang, Gabriel Bender, Quoc V. Le, Jiquan Ngiam Date: Apr. 2019 Arxiv: 1904.04971 Published: NIPS 2019 Abstract Convolutional layers are one of the basic building blocks of modern deep neural networks. One fundamental assumption i...

Info Title: Selective Kernel Networks Task: Image Classification Author: Xiang Li , Wenhai Wang, Xiaolin Hu and Jian Yang Date: Mar. 2019 Arxiv: 1903.06586 Published: CVPR 2019 Highlights Dynamic sleection mechanism in CNNs that allows each neuron to adaptivel adjust its receptive fied size based on multiple scales of input info...

Info Title: Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation Author: Hang Gao, Xizhou Zhu , Steve Lin, Jifeng Dai3 Date: Oct. 2019 Arxiv: 1910.02940 Highlights Resample the original kernel space towards recovering the deformation of objects. Directly adapting the ERF whil...