# Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection

arXiv: https://arxiv.org/abs/2212.06493 · HTML: https://mlsanity.com/paper/2212.06493/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 56 references that are in the map.
- First posted on arXiv 13 Dec 2022.

## Builds on (most cited first, 30 of 38)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Cascaded Partial Decoder for Fast and Accurate Salient Object Detection](https://mlsanity.com/paper/1904.08739/) (2019)
- [Multi-scale Interactive Network for Salient Object Detection](https://mlsanity.com/paper/2007.09062/) (2020)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [F3Net: Fusion, Feedback and Focus for Salient Object Detection](https://mlsanity.com/paper/1911.11445/) (2019)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation](https://mlsanity.com/paper/1706.04737/) (2017)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [Weakly-Supervised Salient Object Detection via Scribble Annotations](https://mlsanity.com/paper/2003.07685/) (2020)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Influence Selection for Active Learning](https://mlsanity.com/paper/2108.09331/) (2021)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Specificity-preserving RGB-D Saliency Detection](https://mlsanity.com/paper/2108.08162/) (2021)
- [Active Learning for Deep Detection Neural Networks](https://mlsanity.com/paper/1911.09168/) (2019)
- [Neural Ensemble Search for Uncertainty Estimation and Dataset Shift](https://mlsanity.com/paper/2006.08573/) (2020)
- [Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion](https://mlsanity.com/paper/2103.11832/) (2021)
- [Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence](https://mlsanity.com/paper/2012.04404/) (2020)
- [CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation](https://mlsanity.com/paper/1810.09726/) (2018)
- [Multi-source weak supervision for saliency detection](https://mlsanity.com/paper/1904.00566/) (2019)
- [Active Learning for Cost-Sensitive Classification](https://mlsanity.com/paper/1703.01014/) (2017)
- [TRADI: Tracking deep neural network weight distributions for uncertainty estimation](https://mlsanity.com/paper/1912.11316/) (2019)
- [Disentangled High Quality Salient Object Detection](https://mlsanity.com/paper/2108.03551/) (2021)

## Built on by (most cited first, 2 of 2)

- [A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation](https://mlsanity.com/paper/2411.16370/) (2024)
- [Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detection](https://mlsanity.com/paper/2412.16840/) (2024)

## Abstract (arXiv)

Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised version. This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset. To prove this conjecture, we proposed a novel yet effective adversarial trajectory-ensemble active learning (ATAL). Our contributions are three-fold: 1) Our proposed adversarial attack triggering uncertainty can conquer the overconfidence of existing active learning methods and accurately locate these uncertain pixels. 2) Our proposed trajectory-ensemble uncertainty estimation method maintains the advantages of the ensemble networks while significantly reducing the computational cost. 3) Our proposed relationship-aware diversity sampling algorithm can conquer oversampling while boosting performance. Experimental results show that our ATAL can find such a point-labeled dataset, where a saliency model trained on it obtained 97% -- 99% performance of its fully-supervised version with only ten annotated points per image.