# Spatially Adaptive Computation Time for Residual Networks

arXiv: https://arxiv.org/abs/1612.02297 · HTML: https://mlsanity.com/paper/1612.02297/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2016.

## Built on by (most cited first, 30 of 118)

- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [Scalable Adaptive Computation for Iterative Generation](https://mlsanity.com/paper/2212.11972/) (2022)
- [Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2105.15075/) (2021)
- [MOOD: Multi-level Out-of-distribution Detection](https://mlsanity.com/paper/2104.14726/) (2021)
- [SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events](https://mlsanity.com/paper/2103.15538/) (2021)
- [Adaptive Focus for Efficient Video Recognition](https://mlsanity.com/paper/2105.03245/) (2021)
- [Spatially-Adaptive Image Restoration using Distortion-Guided Networks](https://mlsanity.com/paper/2108.08617/) (2021)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://mlsanity.com/paper/2104.13400/) (2021)
- [PnP-DETR: Towards Efficient Visual Analysis with Transformers](https://mlsanity.com/paper/2109.07036/) (2021)
- [A Survey on Green Deep Learning](https://mlsanity.com/paper/2111.05193/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models](https://mlsanity.com/paper/2203.15859/) (2022)
- [Revisiting Token Pruning for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2306.07050/) (2023)
- [AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition](https://mlsanity.com/paper/2102.05775/) (2021)
- [AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning](https://mlsanity.com/paper/2412.03248/) (2024)
- [Glance and Focus Networks for Dynamic Visual Recognition](https://mlsanity.com/paper/2201.03014/) (2022)
- [Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images](https://mlsanity.com/paper/2303.14488/) (2023)
- [MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks](https://mlsanity.com/paper/2412.20522/) (2024)
- [Zero Time Waste: Recycling Predictions in Early Exit Neural Networks](https://mlsanity.com/paper/2106.05409/) (2021)
- [Path Independent Equilibrium Models Can Better Exploit Test-Time Computation](https://mlsanity.com/paper/2211.09961/) (2022)
- [AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition](https://mlsanity.com/paper/2112.14238/) (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)
- [Dynamic Perceiver for Efficient Visual Recognition](https://mlsanity.com/paper/2306.11248/) (2023)
- [Skip-Convolutions for Efficient Video Processing](https://mlsanity.com/paper/2104.11487/) (2021)

## Abstract (arXiv)

This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic. It is therefore applicable without any modifications to a wide range of computer vision problems such as image classification, object detection and image segmentation. We present experimental results showing that this model improves the computational efficiency of Residual Networks on the challenging ImageNet classification and COCO object detection datasets. Additionally, we evaluate the computation time maps on the visual saliency dataset cat2000 and find that they correlate surprisingly well with human eye fixation positions.