• Publications
  • Influence
CCNet: Criss-Cross Attention for Semantic Segmentation
TLDR
We propose a Criss-Cross Network (CCNet) for obtaining contextual information of all the pixels on its criss-cross path. Expand
Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
TLDR
We investigate a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems and propose a new adversarial erasing approach for localizing and expanding object regions progressively. Expand
Adversarial Complementary Learning for Weakly Supervised Object Localization
TLDR
In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. Expand
HCP: A Flexible CNN Framework for Multi-Label Image Classification
TLDR
We propose a flexible deep CNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrary number of object segment hypotheses are taken as the inputs, then a shared CNN is connected with each hypothesis, and finally the CNN output results from different hypotheses are aggregated with max pooling to produce the ultimate multi-label predictions. Expand
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation
TLDR
In this paper, we propose a simple to complex (STC) framework in which only image-level annotations are utilized to learn DCNNs for semantic segmentation. Expand
Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification
TLDR
We propose a Self-similarity Grouping (SSG) approach, which exploits the potential similarity (from the global body to local parts) of unlabeled samples to build multiple clusters from different views automatically. Expand
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
TLDR
We revisit the dilated convolution [1] and reveal how it can be utilized in a novel way to effectively overcome this critical limitation of weakly supervised segmentation approaches. Expand
Horizontal Pyramid Matching for Person Re-identification
TLDR
We propose a simple yet effective Horizontal Pyramid Matching (HPM) approach to fully exploit various partial information of a given person, so that correct person candidates can be still identified even even some key parts are missing. Expand
Self-produced Guidance for Weakly-supervised Object Localization
TLDR
We propose to generate Self-produced Guidance (SPG) masks which separate the foreground i.e., the object of interest, from the background to provide the classification networks with spatial correlation information of pixels. Expand
SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
TLDR
We propose a simple yet effective similarity guidance network to tackle the one-shot (SG-One) segmentation problem. Expand
...
1
2
3
4
5
...