Deeply Supervised Salient Object Detection with Short Connections Qibin Hou, Ming-Ming Cheng, Xiaowei Hu, Ali Borji, Zhuowen Tu, Philip H. S. Torr Observations:

Slides:

Advertisements

Similar presentations

Ming-Ming Cheng 1 Ziming Zhang 2 Wen-Yan Lin 3 Philip H. S. Torr 1 1 Oxford University, 2 Boston University 3 Brookes Vision Group Training a generic objectness.

Advertisements

Leveraging Stereopsis for Saliency Analysis

|| Dmitry Laptev, Joachim M. Buhmann Machine Learning Lab, ETH Zurich 05/09/14Dmitry Laptev1 Convolutional Decision Trees.

Learning Convolutional Feature Hierarchies for Visual Recognition

On the Relationship between Visual Attributes and Convolutional Networks Paper ID - 52.

What is the Best Multi-Stage Architecture for Object Recognition Kevin Jarrett, Koray Kavukcuoglu, Marc’ Aurelio Ranzato and Yann LeCun Presented by Lingbo.

Presented by: Kamakhaya Argulewar Guided by: Prof. Shweta V. Jain

Fully Convolutional Networks for Semantic Segmentation

When deep learning meets object detection: Introduction to two technologies: SSD and YOLO Wenchi Ma.

Environmental Remote Sensing GEOG 2021

Recent developments in object detection

Big data classification using neural network

Convolutional Sequence to Sequence Learning

Convolutional Neural Network

Deeply learned face representations are sparse, selective, and robust

Object Detection based on Segment Masks

HFS: Hierarchical Feature Selection for Efficient Image Segmentation

Automatic Lung Cancer Diagnosis from CT Scans (Week 2)

Levels of Processing Memory Model (LoP)

MR images analysis of glioma

Depth estimation and Plane detection

Journal of Vision. 2017;17(4):9. doi: / Figure Legend:

Combining CNN with RNN for scene labeling (segmentation)

RIVER SEGMENTATION FOR FLOOD MONITORING

Synthesis of X-ray Projections via Deep Learning

Outline Texture modeling - continued Filtering-based approaches.

Addy Satija and Jef Caers Department of Energy Resources Engineering

Presenter: Hajar Emami

CS6890 Deep Learning Weizhen Cai

R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.

with Daniel L. Silver, Ph.D. Christian Frey, BBA April 11-12, 2017

Enhanced-alignment Measure for Binary Foreground Map Evaluation

Fully Convolutional Networks for Semantic Segmentation

Human-level control through deep reinforcement learning

Computer Vision James Hays

Convolutional Neural Networks

Image Classification.

A Comparative Study of Convolutional Neural Network Models with Rosenblatt’s Brain Model Abu Kamruzzaman, Atik Khatri , Milind Ikke, Damiano Mastrandrea,

Bringing Salient Object Detection to the Foreground

Enhanced-alignment Measure for Binary Foreground Map Evaluation

CSC 578 Neural Networks and Deep Learning

CornerNet: Detecting Objects as Paired Keypoints

A Proposal Defense On Deep Residual Network For Face Recognition Presented By SAGAR MISHRA MECE

Semantic segmentation

GAN Applications.

Visualizing and Understanding Convolutional Networks

Analysis of Trained CNN (Receptive Field & Weights of Network)

RCNN, Fast-RCNN, Faster-RCNN

Short-term Memory Notes (based on photocopies from class on Sept. 14)

Deep Learning Some slides are from Prof. Andrew Ng of Stanford.

Autoencoders hi shea autoencoders Sys-AI.

边缘检测年度进展概述 Ming-Ming Cheng Media Computing Lab, Nankai University

Heterogeneous convolutional neural networks for visual recognition

Face Recognition: A Convolutional Neural Network Approach

Department of Computer Science Ben-Gurion University of the Negev

A unified extension of lstm to deep network

U-Net: Convolutional Network for Segmentation

Applications of Capsules

one-input multi-output architecture

Motivation State-of-the-art two-stage instance segmentation methods depend heavily on feature localization to produce masks.

Semantic Segmentation

Object Detection Implementations

What's New in eCognition 9

Learning Deconvolution Network for Semantic Segmentation

CSC 578 Neural Networks and Deep Learning

Week 7 Presentation Ngoc Ta Aidean Sharghi

Point Set Representation for Object Detection and Beyond

Shengcong Chen, Changxing Ding, Minfeng Liu 2018

Presentation transcript:

Deeply Supervised Salient Object Detection with Short Connections Qibin Hou, Ming-Ming Cheng, Xiaowei Hu, Ali Borji, Zhuowen Tu, Philip H. S. Torr Observations: Additional Changes: Problem: The goal in salient object detection is to identify the most visually distinctive objects or regions in an image and then segment them out from the back- ground. To enhance the ability of each side output, we also add another two convolutional layers with different kernel sizes to each side output. Following HED, we add a stack of side supervisions after each stage to see the different behaviors brought by multi-level features. Deeper layers are able to accurately locate the salient objects while lower layers encode rich detailed features which are required for refinement. Results and Failure Cases: FCN-Based Methods: The Architecture of Our DSS: Illustration of different architectures. (a) Hypercolumn [1], (b) FCN-8s [2], (c) HED [3], (d) and (e) different patterns of our proposed architecture. A series of short connections are introduced in our architecture Introducing short connections to the skip-layer structure within the HED architecture. High-level features can be transformed to shallower side-output layers. Shallower side-output can help refine the sparse and irregular prediction maps from deeper side-output layers. for combining the advantages of both deeper layers and shallower layers. While our approach can be extended to a variety of different structures, we just list two typical ones. Source code: https://mmcheng.net/dss/