Data to 7 Oct 2026

Resolution Adaptive Networks for Efficient Inference

arXiv 2003.07326 ↗First posted 16 Mar 2020cs.CVcited by 146

Not on the map. Why?

Abstract (arXiv)

Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks. Existing works mainly exploit architecture redundancy in network depth or width. In this paper, we focus on spatial redundancy of input samples and propose a novel Resolution Adaptive Network (RANet), which is inspired by the intuition that low-resolution representations are sufficient for classifying "easy" inputs containing large objects with prototypical features, while only some "hard" samples need spatially detailed information. In RANet, the input images are first routed to a lightweight sub-network that efficiently extracts low-resolution representations, and those samples with high prediction confidence will exit early from the network without being further processed. Meanwhile, high-resolution paths in the network maintain the capability to recognize the "hard" samples. Therefore, RANet can effectively reduce the spatial redundancy involved in inferring high-resolution inputs. Empirically, we demonstrate the effectiveness of the proposed RANet on the CIFAR-10, CIFAR-100 and ImageNet datasets in both the anytime prediction setting and the budgeted batch classification setting.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 24; 2023: 31; 2024: 37; 2025: 12; 2026: 12.

146 papers.

Sort:

By area:

2021Dynamic Neural Networks: A Surveycited by 405
2021AdaViT: Adaptive Tokens for Efficient Vision Transformercited by 360
2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
2023FLatten Transformer: Vision Transformer using Focused Linear Attentioncited by 170
2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143
2021IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformerscited by 127
2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Executioncited by 116
2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 114
2024Not All Layers of LLMs Are Necessary During Inferencecited by 95
2021Adaptive Focus for Efficient Video Recognitioncited by 76
2021Adaptive Inference through Early-Exit Networks: Design, Challenges and Directionscited by 74
2021Revisiting Locally Supervised Learning: an Alternative to End-to-end Trainingcited by 71

38 more

2022CF-ViT: A General Coarse-to-Fine Method for Vision Transformercited by 63
2024Dynamic Diffusion Transformercited by 60
2021FrameExit: Conditional Early Exiting for Efficient Video Recognitioncited by 59
2023Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantizationcited by 59
2021A Survey on Green Deep Learningcited by 52
2023Adaptive Rotated Convolution for Rotated Object Detectioncited by 51
2022Learning to Weight Samples for Dynamic Early-exiting Networkscited by 44
2022EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbonescited by 42
2022Glance and Focus Networks for Dynamic Visual Recognitioncited by 41
2021Zero Time Waste: Recycling Predictions in Early Exit Neural Networkscited by 39
2021AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognitioncited by 37
2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
2024A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMscited by 35
2021CondenseNet V2: Sparse Feature Reactivation for Deep Networkscited by 34
2023Dynamic Perceiver for Efficient Visual Recognitioncited by 33
2021Dynamic Resolution Networkcited by 31
2021MicroNet: Improving Image Recognition with Extremely Low FLOPscited by 26
2023Latency-aware Unified Dynamic Networks for Efficient Image Recognitioncited by 26
2024Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Networkcited by 26
2022DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detectioncited by 25
2022Latency-aware Spatial-wise Dynamic Networkscited by 25
2024Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptationcited by 25
2023Dynamic Grained Encoder for Vision Transformerscited by 24
2024Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Modelcited by 22
2021SHARP: Environment and Person Independent Activity Recognition with Commodity IEEE 802.11 Access Pointscited by 20
2023Fixing Overconfidence in Dynamic Neural Networkscited by 19
2024DyFADet: Dynamic Feature Aggregation for Temporal Action Detectioncited by 18
2021AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inferencecited by 16
2022DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networkscited by 16
2023Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicitycited by 16
2024EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Trainingcited by 16
2023Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Modelscited by 15
2023DynamicDet: A Unified Dynamic Architecture for Object Detectioncited by 15
2023Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNNcited by 15
2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
2022Super Vision Transformercited by 13
2022DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generationcited by 13
2023Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecyclecited by 13

50 most cited of 146 All 146 (JSON)