# AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling

arXiv: https://arxiv.org/abs/2111.00772 · HTML: https://mlsanity.com/paper/2111.00772/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 95 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 30 of 53)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation](https://mlsanity.com/paper/1611.06612/) (2016)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Deep Learning for Image Super-resolution: A Survey](https://mlsanity.com/paper/1902.06068/) (2019)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)

## Built on by (most cited first, 30 of 47)

- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation](https://mlsanity.com/paper/2411.09153/) (2024)
- [Training-Free Efficient Video Generation via Dynamic Token Carving](https://mlsanity.com/paper/2505.16864/) (2025)
- [MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis](https://mlsanity.com/paper/2503.13319/) (2025)
- [The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction](https://mlsanity.com/paper/2204.13340/) (2022)
- [CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation](https://mlsanity.com/paper/2506.23121/) (2025)
- [LAVIB: A Large-scale Video Interpolation Benchmark](https://mlsanity.com/paper/2406.09754/) (2024)
- [Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration](https://mlsanity.com/paper/2508.14483/) (2025)
- [LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs](https://mlsanity.com/paper/2507.00505/) (2025)
- [AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content](https://mlsanity.com/paper/2409.17256/) (2024)
- [Sparsity-guided Network Design for Frame Interpolation](https://mlsanity.com/paper/2209.04551/) (2022)
- [FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space](https://mlsanity.com/paper/2602.02092/) (2026)
- [FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters](https://mlsanity.com/paper/2603.01685/) (2026)
- [From Ideal to Real: Stable Video Object Removal under Imperfect Conditions](https://mlsanity.com/paper/2603.09283/) (2026)
- [Convex Hull Prediction for Adaptive Video Streaming by Recurrent Learning](https://mlsanity.com/paper/2206.04877/) (2022)
- [RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution](https://mlsanity.com/paper/2307.02897/) (2023)
- [Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs](https://mlsanity.com/paper/2506.09215/) (2025)
- [Physics-Aware Video Instance Removal Benchmark](https://mlsanity.com/paper/2604.05898/) (2026)
- [Efficient Feature Extraction for High-resolution Video Frame Interpolation](https://mlsanity.com/paper/2211.14005/) (2022)
- [SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition](https://mlsanity.com/paper/2509.25723/) (2025)
- [EditTrack: Detecting and Attributing AI-assisted Image Editing](https://mlsanity.com/paper/2510.01173/) (2025)
- [LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing](https://mlsanity.com/paper/2605.11508/) (2026)
- [Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothing](https://mlsanity.com/paper/2210.10526/) (2022)
- [DiffVQA: Video Quality Assessment Using Diffusion Feature Extractor](https://mlsanity.com/paper/2505.03261/) (2025)
- [Semantic Frame Interpolation](https://mlsanity.com/paper/2507.05173/) (2025)
- [Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior](https://mlsanity.com/paper/2508.10779/) (2025)
- [Autoregressive Video Autoencoder with Decoupled Temporal and Spatial Context](https://mlsanity.com/paper/2512.11293/) (2025)
- [ELLMPEG: An Edge-based Agentic LLM Video Processing Tool](https://mlsanity.com/paper/2602.00028/) (2026)
- [Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model](https://mlsanity.com/paper/2602.03529/) (2026)
- [MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation](https://mlsanity.com/paper/2302.09411/) (2023)

## Abstract (arXiv)

Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional operations. Their goal is to produce downsampled volumes that closely resemble the input volume while, ideally, also being computationally and memory efficient. Meeting both these requirements remains a challenge. To this end, we propose an adaptive and exponentially weighted pooling method: adaPool. Our method learns a regional-specific fusion of two sets of pooling kernels that are based on the exponent of the Dice-Sorensen coefficient and the exponential maximum, respectively. AdaPool improves the preservation of detail on a range of tasks including image and video classification and object detection. A key property of adaPool is its bidirectional nature. In contrast to common pooling methods, the learned weights can also be used to upsample activation maps. We term this method adaUnPool. We evaluate adaUnPool on image and video super-resolution and frame interpolation. For benchmarking, we introduce Inter4K, a novel high-quality, high frame-rate video dataset. Our experiments demonstrate that adaPool systematically achieves better results across tasks and backbones, while introducing a minor additional computational and memory overhead.