Semi-supervised Salient Object Detection with Effective Confidence Estimation
Not on the map. Why?
Abstract (arXiv)
The success of existing salient object detection models relies on a large pixel-wise labeled training dataset, which is time-consuming and expensive to obtain. We study semi-supervised salient object detection, with access to a small number of labeled samples and a large number of unlabeled samples. Specifically, we present a pseudo label based learn-ing framework with a Conditional Energy-based Model. We model the stochastic nature of human saliency labels using the stochastic latent variable of the Conditional Energy-based Model. It further enables generation of a high-quality pixel-wise uncertainty map, highlighting the reliability of corresponding pseudo label generated for the unlabeled sample. This minimises the contribution of low-certainty pseudo labels in optimising the model, preventing the error propagation. Experimental results show that the proposed strategy can effectively explore the contribution of unlabeled data. With only 1/16 labeled samples, our model achieves competitive performance compared with state-of-the-art fully-supervised models.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 59 of its 111 references that are in the map. First posted on arXiv 28 Dec 2021.
Builds on
59 of 111 references.
References · 59
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2016Gaussian Error Linear Units (GELUs)cited by 3,502
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
- 2015Variational Inference with Normalizing Flowscited by 2,170
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
- 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
38 more
- 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
- 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
- 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
- 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
- 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
- 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
- 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
- 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
- 2017Snapshot Ensembles: Train 1, get M for freecited by 350
- 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
- 2015Semi-Supervised Learning with Ladder Networkscited by 247
- 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
- 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
- 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 212
- 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
- 2016Deeply supervised salient object detection with short connectionscited by 196
- 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
- 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
- 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
- 2021Visual Saliency Transformercited by 175
- 2016A Theory of Generative ConvNetcited by 174
- 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 148
- 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
- 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
- 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
- 2015Salient Object Detection: A Benchmarkcited by 131
- 2019Pyramid Feature Attention Network for Saliency detectioncited by 128
- 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
- 2021Uncertainty-aware Joint Salient Object and Camouflaged Object Detectioncited by 114
- 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
- 2020Learning Latent Space Energy-Based Prior Modelcited by 104
- 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
- 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
- 2020Weakly-Supervised Salient Object Detection via Scribble Annotationscited by 96
- 2017Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detectioncited by 93
- 2020Masksembles for Uncertainty Estimationcited by 88
- 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
- 2016Auxiliary Deep Generative Modelscited by 72
50 most cited of 59 All 59 (JSON)
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 0; 2026: 1.
3 papers.