Learning Hierarchical Features for Scene Labeling

By Clément Farabet, Camille Couprie, Laurent Najman, Yann LeCun. 2013

2,781 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Fully convolutional networks for semantic segmentation (2014, methodology): “Our approach does not make use of pre-and post-processing complications, including superpixels [6, 14], proposals [14, 12], or post-hoc reﬁnement by random ﬁelds or local classiﬁers [6, 14].”
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks (2013, background): “Applications range from biological image analysis [21], to obstacle tagging for mobile robots [10] to tagging of photos [7].”
Network In Network (2013, methodology): “Detection results can be achieved based on the category level feature maps in the same ﬂavor as in the scene labeling work of Farabet et al. [20].”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “Our general strategy is to rely heavily on the val set and use some of the train images as an auxiliary source of positive examples.”
Colorful Image Colorization (2016, methodology): “Class-balanced metrics are commonly employed in other tasks such object detection [19] and semantic segmentation [25].”
Hypercolumns for object segmentation and fine-grained localization (2014, methodology): “[15] combine CNN outputs from multiple scales of an image to do semantic segmentation.”
Beyond Skip Connections: Top-Down Modulation for Object Detection (2016, methodology): “For example, [4, 10, 22, 42] combine features from multiple layers for the final classifier; while [4, 42] use subsampled features from finer scales, [10, 22] upsample the features to the finest scale and use their combination.”
Shape-aware Instance Segmentation (2016, background): “Over the years, much progress has been made on the task of category-level semantic segmentation, particularly since the advent of Deep Convolutional Neural Networks (CNNs) [9, 22, 3].”
Learning to Refine Object Segments (2016, methodology): “Features can be computed independently at each scale [13], or the output from one scale can be used as additional input to the next finer scale [14,15].”
Simultaneous Detection and Segmentation (2014, methodology): “They have since been used in a variety of tasks, including detection [29,28] and semantic segmentation [12].”
Perceiver IO: A General Architecture for Structured Inputs & Outputs (2021, background): “As hardware acceleration grew more powerful and neural nets proved themselves in image understanding [41, 101, 78], interest intensified: autoregressive models were developed that could take samples of handwriting and complete them [28], and new convolutional network designs led to good results in s”
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, methodology): “Our new version can better segment objects at multiple scales, via either multi-scale input processing [17], [39], [40] or the proposed ASPP.”
Deep Interactive Object Selection (2016, methodology): “Then, For the efﬁciency of data storage, we truncate u tij to 255.”
Holistically-Nested Edge Detection (2015, background): “strated in Fig2(c). This strategy can happen at both the training stage (as data augmentation) and at the testing stage (as “ensemble testing”). One notable example is the tiedweight pyramid networks [8]. This approach is also common in non-deep-learning based methods [6]. Note that ensemble testing”
Perceptual Losses for Real-Time Style Transfer and Super-Resolution (2016, methodology): “Semantic segmentation methods [3,5,12,13,14,15] produce dense scene labels by running a network in a fully-convolutional manner over an input image, training with a per-pixel classiﬁcation loss.”
Multi-Scale Context Aggregation by Dilated Convolutions (2015, background): “Another approach involves providing multiple rescaled versions of the image as input to the network and combining the predictions obtained for these multiple inputs (Farabet et al., 2013; Lin et al., 2015; Chen et al., 2015b).”
Scene Parsing through ADE20K Dataset (2017, background): “With the success of convolutional neural networks (CNN) for image classification [16], there is growing interest for semantic image parsing using CNNs with dense output, such as the multiscale CNN [11], recurrent CNN [25], fully CNN [19], deconvolutional neural networks [24], encoder-decoder SegNet ”