# Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition

arXiv: https://arxiv.org/abs/1807.03848 · HTML: https://mlsanity.com/paper/1807.03848/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2018.

## Built on by (most cited first, 22 of 22)

- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [MoViNets: Mobile Video Networks for Efficient Video Recognition](https://mlsanity.com/paper/2103.11511/) (2021)
- [DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation](https://mlsanity.com/paper/2106.06716/) (2021)
- [MOOD: Multi-level Out-of-distribution Detection](https://mlsanity.com/paper/2104.14726/) (2021)
- [QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results](https://mlsanity.com/paper/2112.10074/) (2021)
- [WaveMix: A Resource-efficient Neural Network for Image Analysis](https://mlsanity.com/paper/2205.14375/) (2022)
- [Accurate Leukocyte Detection Based on Deformable-DETR and Multi-Level Feature Fusion for Aiding Diagnosis of Blood Diseases](https://mlsanity.com/paper/2401.00926/) (2024)
- [Metaethical Perspectives on 'Benchmarking' AI Ethics](https://mlsanity.com/paper/2204.05151/) (2022)
- [AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning](https://mlsanity.com/paper/2303.01589/) (2023)
- [SENetV2: Aggregated dense layer for channelwise and global representations](https://mlsanity.com/paper/2311.10807/) (2023)
- [AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2312.05928/) (2023)
- [Busy-Quiet Video Disentangling for Video Classification](https://mlsanity.com/paper/2103.15584/) (2021)
- [Deepfake Detection: A Comparative Analysis](https://mlsanity.com/paper/2308.03471/) (2023)
- [big.LITTLE Vision Transformer for Efficient Visual Recognition](https://mlsanity.com/paper/2410.10267/) (2024)
- [Kernel Inversed Pyramidal Resizing Network for Efficient Pavement Distress Recognition](https://mlsanity.com/paper/2212.01790/) (2022)
- [CTRL-F: Pairing Convolution with Transformer for Image Classification via Multi-Level Feature Cross-Attention and Representation Learning Fusion](https://mlsanity.com/paper/2407.06673/) (2024)
- [SpatioTemporal Focus for Skeleton-based Action Recognition](https://mlsanity.com/paper/2203.16767/) (2022)
- [SDA-xNet: Selective Depth Attention Networks for Adaptive Multi-scale Feature Representation](https://mlsanity.com/paper/2209.10327/) (2022)
- [Squeeze aggregated excitation network](https://mlsanity.com/paper/2308.13343/) (2023)
- [Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion](https://mlsanity.com/paper/2403.10803/) (2024)
- [Harnessing The Power of Attention For Patch-Based Biomedical Image Classification](https://mlsanity.com/paper/2404.00949/) (2024)

## Abstract (arXiv)

In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has different computational complexity at different branches. Through frequent merging of features from branches at distinct scales, our model obtains multi-scale features while using less computation. The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks,using popular architectures including ResNet and ResNeXt. For object recognition, our approach reduces computation by 33% on object recognition while improving accuracy with 0.9%. Furthermore, our model surpasses state-of-the-art CNN acceleration approaches by a large margin in accuracy and FLOPs reduction. On the task of speech recognition, our proposed multi-scale CNNs save 30% FLOPs with slightly better word error rates, showing good generalization across domains. The codes are available at https://github.com/IBM/BigLittleNet