# PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection

arXiv: https://arxiv.org/abs/1812.06314 · HTML: https://mlsanity.com/paper/1812.06314/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2018.

## Built on by (most cited first, 28 of 28)

- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Weakly Supervised Video Salient Object Detection](https://mlsanity.com/paper/2104.02391/) (2021)
- [Artificial Intelligence for the Metaverse: A Survey](https://mlsanity.com/paper/2202.10336/) (2022)
- [Background-Click Supervision for Temporal Action Localization](https://mlsanity.com/paper/2111.12449/) (2021)
- [A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels](https://mlsanity.com/paper/2209.02957/) (2022)
- [GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding](https://mlsanity.com/paper/2311.11863/) (2023)
- [Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark](https://mlsanity.com/paper/2406.00917/) (2024)
- [Salient Object Detection in Optical Remote Sensing Images Driven by Transformer](https://mlsanity.com/paper/2309.08206/) (2023)
- [Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/2112.01932/) (2021)
- [Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection](https://mlsanity.com/paper/2405.09782/) (2024)
- [Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance](https://mlsanity.com/paper/2110.00698/) (2021)
- [DC-Net: Divide-and-Conquer for Salient Object Detection](https://mlsanity.com/paper/2305.14955/) (2023)
- [Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt](https://mlsanity.com/paper/2302.01171/) (2023)
- [Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2204.02791/) (2022)
- [Unified-modal Salient Object Detection via Adaptive Prompt Learning](https://mlsanity.com/paper/2311.16835/) (2023)
- [Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation](https://mlsanity.com/paper/2405.13388/) (2024)
- [RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation](https://mlsanity.com/paper/2609.12622/) (2026)
- [Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration](https://mlsanity.com/paper/2102.04046/) (2021)
- [Sharp Eyes: A Salient Object Detector Working The Same Way as Human Visual Characteristics](https://mlsanity.com/paper/2301.07431/) (2023)
- [A Novel Wide-Area Multiobject Detection System with High-Probability Region Searching](https://mlsanity.com/paper/2405.04589/) (2024)
- [GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigm](https://mlsanity.com/paper/2508.07585/) (2025)
- [Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning](https://mlsanity.com/paper/2510.08442/) (2025)
- [Semi-Supervised Cross-Modal Salient Object Detection with U-Structure Networks](https://mlsanity.com/paper/2208.04361/) (2022)
- [FIPGNet:Pyramid grafting network with feature interaction strategies](https://mlsanity.com/paper/2407.04085/) (2024)
- [Towards Open World Detection: A Survey](https://mlsanity.com/paper/2508.16527/) (2025)
- [Graph-Based Uncertainty Modeling and Multimodal Fusion for Salient Object Detection](https://mlsanity.com/paper/2508.20415/) (2025)
- [Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach](https://mlsanity.com/paper/2509.15573/) (2025)
- [A Study on Real-time Object Detection using Deep Learning](https://mlsanity.com/paper/2602.15926/) (2026)

## Abstract (arXiv)

In saliency detection, every pixel needs contextual information to make saliency prediction. Previous models usually incorporate contexts holistically. However, for each pixel, usually only part of its context region is useful and contributes to its prediction, while some other part may serve as noises and distractions. In this paper, we propose a novel pixel-wise contextual attention network, ie PiCANet, to learn to selectively attend to informative context locations at each pixel. Specifically, PiCANet generates an attention map over the context region of each pixel, where each attention weight corresponds to the relevance of a context location w.r.t the referred pixel. Then, attentive contextual features can be constructed via selectively incorporating the features of useful context locations with the learned attention. We propose three specific formulations of the PiCANet via embedding the pixel-wise contextual attention mechanism into the pooling and convolution operations with attending to global or local contexts. All the three models are fully differentiable and can be integrated with CNNs with joint training. We introduce the proposed PiCANets into a U-Net architecture for salient object detection. Experimental results indicate that the proposed PiCANets can significantly improve the saliency detection performance. The generated global and local attention can learn to incorporate global contrast and smoothness, respectively, which help localize salient objects more accurately and highlight them more uniformly. Consequently, our saliency model performs favorably against other state-of-the-art methods. Moreover, we also validate that PiCANets can also improve semantic segmentation and object detection performances, which further demonstrates their effectiveness and generalization ability.