• Publications
  • Influence
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
TLDR
We present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections. Expand
  • 1,192
  • 169
  • PDF
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
TLDR
We present a deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF. Expand
  • 656
  • 65
  • PDF
Fast Supervised Hashing with Decision Trees for High-Dimensional Data
TLDR
We propose to use boosted decision trees for achieving non-linearity in hashing, which are fast to train and evaluate, hence more suitable for hashing with high dimensional data. Expand
  • 355
  • 61
  • PDF
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
TLDR
We show how to improve semantic segmentation through the use of contextual information, specifically, we explore ' patch-patch' context between image regions, and 'patch-background' context. Expand
  • 681
  • 55
  • PDF
Deep convolutional neural fields for depth estimation from a single image
TLDR
We consider the problem of depth estimation from a single monocular image in this work. Expand
  • 594
  • 51
  • PDF
RefineNet : MultiPath Refinement Networks with Identity Mappings for High-Resolution Semantic Segmentation
TLDR
We present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections. Expand
  • 133
  • 32
  • PDF
A General Two-Step Approach to Learning-Based Hashing
TLDR
We propose a flexible yet simple framework that is able to accommodate different types of loss functions and hash functions. Expand
  • 168
  • 24
  • PDF
CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning
TLDR
We present CANet, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available. Expand
  • 68
  • 23
  • PDF
Supervised Hashing Using Graph Cuts and Boosted Decision Trees
TLDR
We propose a flexible yet simple framework that is able to accommodate different types of loss functions and hash functions for solving large-scale binary code inference. Expand
  • 65
  • 16
  • PDF
Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation
TLDR
In this paper, we propose to model structured segmentation data with graphs and apply attentive graph reasoning to propagate label information from support data to query data. Expand
  • 36
  • 10
  • PDF