`

Timezone: »

 
Poster
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
Jie Hu · Li Shen · Samuel Albanie · Gang Sun · Andrea Vedaldi

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 210 #61

While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this work, we propose a simple, lightweight approach for better context exploitation in CNNs. We do so by introducing a pair of operators: gather, which efficiently aggregates feature responses from a large spatial extent, and excite, which redistributes the pooled information to local features. The operators are cheap, both in terms of number of added parameters and computational complexity, and can be integrated directly in existing architectures to improve their performance. Experiments on several datasets show that gather-excite can bring benefits comparable to increasing the depth of a CNN at a fraction of the cost. For example, we find ResNet-50 with gather-excite operators is able to outperform its 101-layer counterpart on ImageNet with no additional learnable parameters. We also propose a parametric gather-excite operator pair which yields further performance gains, relate it to the recently-introduced Squeeze-and-Excitation Networks, and analyse the effects of these changes to the CNN feature activation statistics.

Author Information

Jie Hu (Momenta)
Li Shen (University of Oxford)
Samuel Albanie (Oxford University)
Gang Sun (Momenta)
Andrea Vedaldi (Facebook AI Research and University of Oxford)

More from the Same Authors