Data to 7 Oct 2026

Learning Deconvolution Network for Semantic Segmentation

arXiv 1505.04366 ↗First posted 17 May 2015cs.CVcited by 365

Not on the map. Why?

Abstract (arXiv)

We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and unpooling layers, which identify pixel-wise class labels and predict segmentation masks. We apply the trained network to each proposal in an input image, and construct the final semantic segmentation map by combining the results from all proposals in a simple manner. The proposed algorithm mitigates the limitations of the existing methods based on fully convolutional networks by integrating deep deconvolution network and proposal-wise prediction; our segmentation method typically identifies detailed structures and handles objects in multiple scales naturally. Our network demonstrates outstanding performance in PASCAL VOC 2012 dataset, and we achieve the best accuracy (72.5%) among the methods trained with no external data through ensemble with the fully convolutional network.

Key facts. Cited by 365 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 May 2015.

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: 126; 2022: 90; 2023: 74; 2024: 49; 2025: 20; 2026: 5.

365 papers.

Sort:

By area:

2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
2021Vision Transformers for Dense Predictioncited by 1,789
2023LISA: Reasoning Segmentation via Large Language Modelcited by 770
2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
2021OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communicationcited by 304
2021A Survey of Human-in-the-loop for Machine Learningcited by 214
2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
2021Visual Saliency Transformercited by 175
2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 130
2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129

38 more

2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 114
2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
2022ReSTR: Convolution-free Referring Image Segmentation Using Transformerscited by 112
2021Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentationcited by 111
2022Hyperbolic Image Segmentationcited by 101
2022Self-Support Few-Shot Semantic Segmentationcited by 96
2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
2022HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentationcited by 94
2021Iterative Filter Adaptive Network for Single Image Defocus Deblurringcited by 85
2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
2021UACANet: Uncertainty Augmented Context Attention for Polyp Segmentationcited by 61
2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
2023On the Stability-Plasticity Dilemma of Class-Incremental Learningcited by 55
2023Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networkscited by 55
2024LaSagnA: Language-based Segmentation Assistant for Complex Queriescited by 55
2021Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentationcited by 54
2021A Review of Location Encoding for GeoAI: Methods and Applicationscited by 53
2021Decoupled Dynamic Filter Networkscited by 52
2021Capturing Omni-Range Context for Omnidirectional Segmentationcited by 49
2023EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignmentcited by 44
2021CTNet: Context-based Tandem Network for Semantic Segmentationcited by 43
2024Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generationcited by 43
2023See, Say, and Segment: Teaching LMMs to Overcome False Premisescited by 40
2021Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-level Telltalescited by 39
2022RGB-T Semantic Segmentation with Location, Activation, and Sharpeningcited by 39
2021Learning Frequency Domain Approximation for Binary Neural Networkscited by 38
2024In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentationcited by 38
2021Exemplar-Based Open-Set Panoptic Segmentation Networkcited by 37
2022DDColor: Towards Photo-Realistic Image Colorization via Dual Decoderscited by 36
2024Open-Vocabulary Semantic Segmentation with Image Embedding Balancingcited by 35
2023Semi-Supervised Semantic Segmentation via Gentle Teaching Assistantcited by 34

50 most cited of 365 All 365 (JSON)