# You Look Twice: GaterNet for Dynamic Filter Selection in CNNs

arXiv: https://arxiv.org/abs/1811.11205 · HTML: https://mlsanity.com/paper/1811.11205/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2018.

## Built on by (most cited first, 30 of 46)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach](https://mlsanity.com/paper/2102.04170/) (2021)
- [Dynamic Slimmable Network](https://mlsanity.com/paper/2103.13258/) (2021)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition](https://mlsanity.com/paper/2102.05775/) (2021)
- [AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition](https://mlsanity.com/paper/2105.05165/) (2021)
- [Dynamic Network Quantization for Efficient Video Inference](https://mlsanity.com/paper/2108.10394/) (2021)
- [Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization](https://mlsanity.com/paper/2402.18447/) (2024)
- [Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism](https://mlsanity.com/paper/2205.03055/) (2022)
- [Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition](https://mlsanity.com/paper/2209.01425/) (2022)
- [Referring Expression Comprehension Using Language Adaptive Inference](https://mlsanity.com/paper/2306.04451/) (2023)
- [Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN](https://mlsanity.com/paper/2310.09163/) (2023)
- [Spatial Mixture-of-Experts](https://mlsanity.com/paper/2211.13491/) (2022)
- [BasisNet: Two-stage Model Synthesis for Efficient Inference](https://mlsanity.com/paper/2105.03014/) (2021)
- [DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers](https://mlsanity.com/paper/2109.10060/) (2021)
- [Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference](https://mlsanity.com/paper/2312.10193/) (2023)
- [Human-Object Interaction Detection via Weak Supervision](https://mlsanity.com/paper/2112.00492/) (2021)
- [Fast Conditional Network Compression Using Bayesian HyperNetworks](https://mlsanity.com/paper/2205.06404/) (2022)
- [T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXit](https://mlsanity.com/paper/2207.06613/) (2022)
- [A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion](https://mlsanity.com/paper/2501.07451/) (2025)
- [SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision](https://mlsanity.com/paper/2207.06242/) (2022)
- [Progressive Channel-Shrinking Network](https://mlsanity.com/paper/2304.00280/) (2023)
- [Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder](https://mlsanity.com/paper/2401.12167/) (2024)
- [Fine-grained Dynamic Network for Generic Event Boundary Detection](https://mlsanity.com/paper/2407.04274/) (2024)
- [EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception](https://mlsanity.com/paper/2506.21080/) (2025)
- [DynaShare: Task and Instance Conditioned Parameter Sharing for Multi-Task Learning](https://mlsanity.com/paper/2305.17305/) (2023)
- [DIET: Customized Slimming for Incompatible Networks in Sequential Recommendation](https://mlsanity.com/paper/2406.08804/) (2024)
- [CNN Mixture-of-Depths](https://mlsanity.com/paper/2409.17016/) (2024)
- [Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation](https://mlsanity.com/paper/2501.02837/) (2025)

## Abstract (arXiv)

The concept of conditional computation for deep nets has been proposed previously to improve model performance by selectively using only parts of the model conditioned on the sample it is processing. In this paper, we investigate input-dependent dynamic filter selection in deep convolutional neural networks (CNNs). The problem is interesting because the idea of forcing different parts of the model to learn from different types of samples may help us acquire better filters in CNNs, improve the model generalization performance and potentially increase the interpretability of model behavior. We propose a novel yet simple framework called GaterNet, which involves a backbone and a gater network. The backbone network is a regular CNN that performs the major computation needed for making a prediction, while a global gater network is introduced to generate binary gates for selectively activating filters in the backbone network based on each input. Extensive experiments on CIFAR and ImageNet datasets show that our models consistently outperform the original models with a large margin. On CIFAR-10, our model also improves upon state-of-the-art results.