# End-to-end Convolutional Network for Saliency Prediction

arXiv: https://arxiv.org/abs/1507.01422 · HTML: https://mlsanity.com/paper/1507.01422/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2015.

## Built on by (most cited first, 5 of 5)

- [DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors](https://mlsanity.com/paper/2601.12468/) (2026)
- [The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection](https://mlsanity.com/paper/2410.11576/) (2024)
- [Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection](https://mlsanity.com/paper/2508.03108/) (2025)
- [Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition](https://mlsanity.com/paper/2509.06918/) (2025)
- [DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection](https://mlsanity.com/paper/2604.23729/) (2026)

## Abstract (arXiv)

The prediction of saliency areas in images has been traditionally addressed with hand crafted features based on neuroscience principles. This paper however addresses the problem with a completely data-driven approach by training a convolutional network. The learning process is formulated as a minimization of a loss function that measures the Euclidean distance of the predicted saliency map with the provided ground truth. The recent publication of large datasets of saliency prediction has provided enough data to train a not very deep architecture which is both fast and accurate. The convolutional network in this paper, named JuntingNet, won the LSUN 2015 challenge on saliency prediction with a superior performance in all considered metrics.