Home

(CoCosNet) Cross-domain Correspondence Learning for Exemplar-based Image Translation Author: Pan Zhang, Bo Zhang, Dong Chen, Lu Yuan, Fang Wen Arxiv: 2004.05571 Project Site Problem exemplar-based image translation Assumption in prior work Previous exemplar-based method only use style code globally. The style code only characterizes t...

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization Author: Peihao Zhu, Rameen Abdal, Yipeng Qin, Peter Wonka Arxiv: 1911.12861 GitHub Problem synthetic image generation Assumption in prior work Starting from SPADE, 1) use only one style code for whole image, 2) insert style code only in the beginning of network. None o...

Semantically Multi-modal Image Synthesis Author: Zeping Zhu, Zhi-liang Xu, Ansheng You, Xiang Bai Arxiv: 2003.12697 GitHub Problem Semantically multi-modal image synthesis (SMIS): generating multi-modal images at the semantic level. Assumption in prior work Previous work seeks to use multiple class-specific generators, constraining its...

Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector Author: Qi Fan, Wei Zhuo, Yu-Wing Tai Arxiv: 1908.01998 GitHub Problem Few-shot object detection: aims to detect objects of unseen class with a few training examples. Insight Central to our method is the Attention-RPN and the multi-relation module which fully exp...

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection(Oral) Author: Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, Stan Z. Li Arxiv: 1912.02424 GitHub Problem Anchor-based VS. Anchor-Free detectors, what’s the true difference Insight We first point out that the essential differenc...

Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics(Oral) Author: Simon Jenni, Hailin Jin, Paolo Favaro Arxiv: 2004.02331 Problem Recognizing the pose of objects from a single image that for learning uses only unlabelled videos and a weak empirical prior on the object poses. Insight Prevent appearance leakage in Cyc...

(FSAF)Feature Selective Anchor-Free Module for Single-Shot Object Detection - CVPR 2019 Our motivation is to let each instance select the best level of feature freely to optimize the network, so there should be no anchor boxes to constrain the feature selection in our module. Instead, we encode the instances in an anchor-free manner to learn ...

CornerNet: Detecting Objects as Paired Keypoints - ECCV 2018 The model detect an object as a pair of bounding box corners grouped together. A convolutional network outputs a heatmap for all top-left corners, a heatmap for all bottom-right corners, and an embedding vector for each detected corner. The network is trained to predict similar embe...

Identity From Here, Pose From There: Self-Supervised Disentanglement and Generation of Objects Using Unlabeled Videos The proposed model takes as input an ID image and a pose image, and generates an output image with the identity of the ID image and the pose of the pose image. Methods The generator takes as input both the identity referen...

SinGAN: Learning a Generative Model From a Single Natural Image(Best Paper Award) Project Page Code Multi-Scale Pipeline Our model consists of a pyramid of GANs, where both training and inference are done in a coarse-to-fine fashion. At each scale, Gn learns to generate image samples in which all the overlappin...