# Weakly-Supervised Spatial Context Networks

Source: [Weakly-Supervised Spatial Context Networks](<https://www.sota2.com/research/paper/68fa654d1e209131cea0970f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:23:52.793Z

Authors: Zuxuan Wu, Larry S. Davis, Leonid Sigal

Published: 2017-04-10T18:15:34.000Z

## Abstract

We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch, within the same image, conditioned on their real-valued relative spatial offset. Unlike auto-encoders, that aim to encode and reconstruct original image patches, our network aims to encode and reconstruct intermediate representations of the spatially offset patches. As such, the network learns a spatially conditioned contextual representation. By testing performance with various patch selection mechanisms we show that focusing on object-centric patches is important, and that using object proposal as a patch selection mechanism leads to the highest improvement in performance. Further, unlike auto-encoders, context encoders \[21\], or other forms of unsupervised feature learning, we illustrate that contextual supervision (with pre-trained model initialization) can improve on existing pre-trained model performance. We build our spatial context networks on top of standard VGG\_19 and CNN\_M architectures and, among other things, show that we can achieve improvements (with no additional explicit supervision) over the original ImageNet pre-trained VGG\_19 and CNN\_M models in object categorization and detection on VOC2007.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1704.02998>)

[PDF](<https://arxiv.org/pdf/1704.02998.pdf>)
