Data to 7 Oct 2026

Hypercolumns for Object Segmentation and Fine-grained Localization

arXiv 1411.5752 ↗First posted 21 Nov 2014cs.CVcited by 128

Not on the map. Why?

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.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Nov 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 25; 2022: 32; 2023: 28; 2024: 16; 2025: 13; 2026: 13.

128 papers.

Sort:

By area:

2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
2022Head2Toe: Utilizing Intermediate Representations for Better Transfer Learningcited by 83
2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
2022Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learningcited by 57
2021Shape or Texture: Understanding Discriminative Features in CNNscited by 52

38 more

2021CTNet: Context-based Tandem Network for Semantic Segmentationcited by 43
2023Single Image Reflection Separation via Component Synergycited by 38
2021Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separationcited by 32
2023CosPGD: an efficient white-box adversarial attack for pixel-wise prediction taskscited by 27
2023Semantic Image Segmentation: Two Decades of Researchcited by 26
2021Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognitioncited by 24
2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
2022Neural Neighbor Style Transfercited by 23
2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
2023Object Detection with Transformers: A Reviewcited by 22
2024Reversible Decoupling Network for Single Image Reflection Removalcited by 22
2021Learning to Downsample for Segmentation of Ultra-High Resolution Imagescited by 19
2022Boosting vision transformers for image retrievalcited by 19
2022Learning Equivariant Segmentation with Instance-Unique Queryingcited by 17
2022Restoring Vision in Hazy Weather with Hierarchical Contrastive Learningcited by 17
2022Learning Hierarchical Image Segmentation For Recognition and By Recognitioncited by 16
2024Language-guided Image Reflection Separationcited by 16
2021Cellular Network Radio Propagation Modeling with Deep Convolutional Neural Networkscited by 15
2023Towards Domain Generalization for ECG and EEG Classification: Algorithms and Benchmarkscited by 14
2021GANORCON: Are Generative Models Useful for Few-shot Segmentation?cited by 13
2022Semantic-Aware Fine-Grained Correspondencecited by 13
2024Neural deformation fields for template-based reconstruction of cortical surfaces from MRIcited by 13
2023Superpixel Transformers for Efficient Semantic Segmentationcited by 12
2023Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentationcited by 10
2024Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separationcited by 10
2021Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Netcited by 9
2025RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extractioncited by 9
2021Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Predictioncited by 8
2022Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehensioncited by 8
2021An Online Riemannian PCA for Stochastic Canonical Correlation Analysiscited by 7
2022GANmouflage: 3D Object Nondetection with Texture Fieldscited by 7
2023Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentationcited by 7
2025A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removalcited by 7
2021Lightweight Monocular Depth with a Novel Neural Architecture Search Methodcited by 6
2022PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarizationcited by 6
2022Multi-task Fusion for Efficient Panoptic-Part Segmentationcited by 6
2023Reciprocal Attention Mixing Transformer for Lightweight Image Restorationcited by 6
2023Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approachcited by 6

50 most cited of 128 All 128 (JSON)