Memory-aided Contrastive Consensus Learning for Co-salient Object Detection (2023-02-28T00:00:00.000000Z)

TL;DR

A novel Memory-aided Contrastive Consensus Learning (MCCL) framework, which is capable of effectively detecting co-salient objects in real time (∼150 fps), and develops an Adversarial Integrity Learning (AIL) strategy to make the segmented regions more likely composed of complete objects with less surrounding noise.

Abstract

Co-salient object detection (CoSOD) aims at detecting common salient objects within a group of relevant source images. Most of the latest works employ the attention mechanism for finding common objects. To achieve accurate CoSOD results with high-quality maps and high efficiency, we propose a novel Memory-aided Contrastive Consensus Learning (MCCL) framework, which is capable of effectively detecting co-salient objects in real time (∼150 fps). To learn better group consensus, we propose the Group Consensus Aggregation Module (GCAM) to abstract the common features of each image group; meanwhile, to make the consensus representation more discriminative, we introduce the Memory-based Contrastive Module (MCM), which saves and updates the consensus of images from different groups in a queue of memories. Finally, to improve the quality and integrity of the predicted maps, we develop an Adversarial Integrity Learning (AIL) strategy to make the segmented regions more likely composed of complete objects with less surrounding noise. Extensive experiments on all the latest CoSOD benchmarks demonstrate that our lite MCCL outperforms 13 cutting-edge models, achieving the new state of the art (∼5.9% and ∼6.2% improvement in S-measure on CoSOD3k and CoSal2015, respectively). Our source codes, saliency maps, and online demos are publicly available at https://github.com/ZhengPeng7/MCCL.

Authors

Peng Zheng

4 papers

Huan Xiong

2 papers

Jie Qin

4 papers

TL;DR

Abstract

Authors

References63 items

Re-Thinking the Relations in Co-Saliency Detection

GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector

Global-and-Local Collaborative Learning for Co-Salient Object Detection

Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection

A Unified Transformer Framework for Group-Based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection

PoolNet+: Exploring the Potential of Pooling for Salient Object Detection

Saliency-Associated Object Tracking

PVT v2: Improved baselines with Pyramid Vision Transformer

DeepACG: Co-Saliency Detection via Semantic-aware Contrast Gromov-Wasserstein Distance

CoSformer: Detecting Co-Salient Object with Transformers

Group Collaborative Learning for Co-Salient Object Detection

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

Salient Object Detection via Integrity Learning

CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Re-Thinking Co-Salient Object Detection

Gradient-Induced Co-Saliency Detection

Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Momentum Contrast for Unsupervised Visual Representation Learning

Employing Deep Part-Object Relationships for Salient Object Detection

Stacked Cross Refinement Network for Edge-Aware Salient Object Detection

Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation

EGNet: Edge Guidance Network for Salient Object Detection

Detecting Robust Co-Saliency with Recurrent Co-Attention Neural Network

Robust Deep Co-Saliency Detection with Group Semantic

DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection

BASNet: Boundary-Aware Salient Object Detection

Co-Occurrent Features in Semantic Segmentation

Learning Correspondence From the Cycle-Consistency of Time

Pyramid Feature Attention Network for Saliency Detection

A Unified Metric Learning-Based Framework for Co-Saliency Detection

Progressive Attention Guided Recurrent Network for Salient Object Detection

Enhanced-alignment Measure for Binary Foreground Map Evaluation

Non-local Neural Networks

Decoupled Weight Decay Regularization

PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection

Structure-Measure: A New Way to Evaluate Foreground Maps

Group-wise Deep Co-saliency Detection

Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework

Feature Pyramid Networks for Object Detection

A Shape-Based Approach for Salient Object Detection Using Deep Learning

Unconstrained Salient Object Detection via Proposal Subset Optimization

Detection of Co-salient Objects by Looking Deep and Wide

Joint Detection and Identification Feature Learning for Person Search

Deep Contrast Learning for Salient Object Detection

Deep networks for saliency detection via local estimation and global search

Saliency detection by multi-context deep learning

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Domain-Adversarial Training of Neural Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Visual saliency based on multiscale deep features

FaceNet: A unified embedding for face recognition and clustering

Saliency Detection via Dense and Sparse Reconstruction

Cluster-Based Co-Saliency Detection

Salient Object Detection: A Discriminative Regional Feature Integration Approach

SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

Global contrast based salient region detection

iCoseg: Interactive co-segmentation with intelligent scribble guidance

Frequency-tuned salient region detection

Object categorization by learned universal visual dictionary

ICNet: Intra-saliency Correlation Network for Co-Saliency Detection

GENERATIVE ADVERSARIAL NETS

Field of Study

Venue Information

Name

Type

URL

Alternate Names