# High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Vision

arXiv: https://arxiv.org/abs/1504.06201 · HTML: https://mlsanity.com/paper/1504.06201/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2015.

## Built on by (most cited first, 24 of 24)

- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [EDTER: Edge Detection with Transformer](https://mlsanity.com/paper/2203.08566/) (2022)
- [RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth](https://mlsanity.com/paper/2108.00616/) (2021)
- [DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection](https://mlsanity.com/paper/2401.02032/) (2024)
- [OmniControlNet: Dual-stage Integration for Conditional Image Generation](https://mlsanity.com/paper/2406.05871/) (2024)
- [Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds](https://mlsanity.com/paper/2101.02381/) (2021)
- [RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses](https://mlsanity.com/paper/2403.01795/) (2024)
- [Lightweight Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2402.00422/) (2024)
- [Practical Edge Detection via Robust Collaborative Learning](https://mlsanity.com/paper/2308.14084/) (2023)
- [Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations](https://mlsanity.com/paper/2312.06716/) (2023)
- [Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization](https://mlsanity.com/paper/2505.18679/) (2025)
- [Learning Deep Morphological Networks with Neural Architecture Search](https://mlsanity.com/paper/2106.07714/) (2021)
- [EdgeNAT: Transformer for Efficient Edge Detection](https://mlsanity.com/paper/2408.10527/) (2024)
- [Learning to Detect Semantic Boundaries with Image-level Class Labels](https://mlsanity.com/paper/2212.07579/) (2022)
- [Boosting Semantic Segmentation with Semantic Boundaries](https://mlsanity.com/paper/2304.09427/) (2023)
- [Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model Estimation](https://mlsanity.com/paper/2308.13779/) (2023)
- [The Ikshana Hypothesis of Human Scene Understanding](https://mlsanity.com/paper/2101.10837/) (2021)
- [Sequential Learning on Liver Tumor Boundary Semantics and Prognostic Biomarker Mining](https://mlsanity.com/paper/2103.05170/) (2021)
- [PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation](https://mlsanity.com/paper/2109.10083/) (2021)
- [Skyline variations allow estimating distance to trees on landscape photos using semantic segmentation](https://mlsanity.com/paper/2201.08816/) (2022)
- [Semantic Network Model for Sign Language Comprehension](https://mlsanity.com/paper/2301.11709/) (2023)
- [ECT: Fine-grained Edge Detection with Learned Cause Tokens](https://mlsanity.com/paper/2308.03092/) (2023)
- [PEdger++: Practical Edge Detection via Assembling Cross Information](https://mlsanity.com/paper/2508.11961/) (2025)
- [Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection](https://mlsanity.com/paper/2603.27661/) (2026)

## Abstract (arXiv)

Most of the current boundary detection systems rely exclusively on low-level features, such as color and texture. However, perception studies suggest that humans employ object-level reasoning when judging if a particular pixel is a boundary. Inspired by this observation, in this work we show how to predict boundaries by exploiting object-level features from a pretrained object-classification network. Our method can be viewed as a "High-for-Low" approach where high-level object features inform the low-level boundary detection process. Our model achieves state-of-the-art performance on an established boundary detection benchmark and it is efficient to run. Additionally, we show that due to the semantic nature of our boundaries we can use them to aid a number of high-level vision tasks. We demonstrate that using our boundaries we improve the performance of state-of-the-art methods on the problems of semantic boundary labeling, semantic segmentation and object proposal generation. We can view this process as a "Low-for-High" scheme, where low-level boundaries aid high-level vision tasks. Thus, our contributions include a boundary detection system that is accurate, efficient, generalizes well to multiple datasets, and is also shown to improve existing state-of-the-art high-level vision methods on three distinct tasks.