110 citations · 365 across the 58 of their papers we have counts for
9 papers · 1 filter
Disentangled Information Bottleneck
Ziqi Pan, Li Niu, Jianfu Zhang +1
The information bottleneck (IB) method is a technique for extracting information that is relevant for predicting the target random variable from the source random variable, which i…
From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation
Zhangxuan Gu, Siyuan Zhou, Li Niu +2
Zero-shot learning has been actively studied for image classification task to relieve the burden of annotating image labels. Interestingly, semantic segmentation task requires more…
Weak-shot Fine-grained Classification via Similarity Transfer
Junjie Chen, Li Niu, Liu Liu +1
Recognizing fine-grained categories remains a challenging task, due to the subtle distinctions among different subordinate categories, which results in the need of abundant annotat…
BargainNet: Background-Guided Domain Translation for Image Harmonization
Wenyan Cong, Li Niu, Jianfu Zhang +2
Image composition is a fundamental operation in image editing field. However, unharmonious foreground and background downgrade the quality of composite image. Image harmonization,…
DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
Yan Hong, Li Niu, Jianfu Zhang +2
Learning to generate new images for a novel category based on only a few images, named as few-shot image generation, has attracted increasing research interest. Several state-of-th…
Context-aware Feature Generation for Zero-shot Semantic Segmentation
Zhangxuan Gu, Siyuan Zhou, Li Niu +2
Existing semantic segmentation models heavily rely on dense pixel-wise annotations. To reduce the annotation pressure, we focus on a challenging task named zero-shot semantic segme…
F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
Yan Hong, Li Niu, Jianfu Zhang +3
In order to generate images for a given category, existing deep generative models generally rely on abundant training images. However, extensive data acquisition is expensive and f…
Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets
Yan Hong, Li Niu, Jianfu Zhang +1
Multi-task Learning (MTL) for classification with disjoint datasets aims to explore MTL when one task only has one labeled dataset. In existing methods, for each task, the unlabele…
MatchingGAN: Matching-based Few-shot Image Generation
Yan Hong, Li Niu, Jianfu Zhang +1
To generate new images for a given category, most deep generative models require abundant training images from this category, which are often too expensive to acquire. To achieve t…