# Hypercolumns for Object Segmentation and Fine-grained Localization

arXiv: https://arxiv.org/abs/1411.5752 · HTML: https://mlsanity.com/paper/1411.5752/

## Key facts

- Cited by 128 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2014.

## Built on by (most cited first, 30 of 128)

- [Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence](https://mlsanity.com/paper/2305.14334/) (2023)
- [A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS](https://mlsanity.com/paper/2304.00501/) (2023)
- [Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization](https://mlsanity.com/paper/2205.07839/) (2022)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning](https://mlsanity.com/paper/2201.03529/) (2022)
- [SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness](https://mlsanity.com/paper/2207.12391/) (2022)
- [Representation Compensation Networks for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.05402/) (2022)
- [Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning](https://mlsanity.com/paper/2212.03220/) (2022)
- [Shape or Texture: Understanding Discriminative Features in CNNs](https://mlsanity.com/paper/2101.11604/) (2021)
- [CTNet: Context-based Tandem Network for Semantic Segmentation](https://mlsanity.com/paper/2104.09805/) (2021)
- [Single Image Reflection Separation via Component Synergy](https://mlsanity.com/paper/2308.10027/) (2023)
- [Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation](https://mlsanity.com/paper/2110.10546/) (2021)
- [CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks](https://mlsanity.com/paper/2302.02213/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition](https://mlsanity.com/paper/2107.12090/) (2021)
- [Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation](https://mlsanity.com/paper/2307.03407/) (2023)
- [Neural Neighbor Style Transfer](https://mlsanity.com/paper/2203.13215/) (2022)
- [Learning Rotation-Equivariant Features for Visual Correspondence](https://mlsanity.com/paper/2303.15472/) (2023)
- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [Reversible Decoupling Network for Single Image Reflection Removal](https://mlsanity.com/paper/2410.08063/) (2024)
- [Learning to Downsample for Segmentation of Ultra-High Resolution Images](https://mlsanity.com/paper/2109.11071/) (2021)
- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [Learning Equivariant Segmentation with Instance-Unique Querying](https://mlsanity.com/paper/2210.00911/) (2022)
- [Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning](https://mlsanity.com/paper/2212.11473/) (2022)
- [Learning Hierarchical Image Segmentation For Recognition and By Recognition](https://mlsanity.com/paper/2210.00314/) (2022)
- [Language-guided Image Reflection Separation](https://mlsanity.com/paper/2402.11874/) (2024)
- [Cellular Network Radio Propagation Modeling with Deep Convolutional Neural Networks](https://mlsanity.com/paper/2110.01848/) (2021)

## Abstract (arXiv)

Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as feature representation. However, the information in this layer may be too coarse to allow precise localization. On the contrary, earlier layers may be precise in localization but will not capture semantics. To get the best of both worlds, we define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel. Using hypercolumns as pixel descriptors, we show results on three fine-grained localization tasks: simultaneous detection and segmentation[22], where we improve state-of-the-art from 49.7[22] mean AP^r to 60.0, keypoint localization, where we get a 3.3 point boost over[20] and part labeling, where we show a 6.6 point gain over a strong baseline.