mlsanityData to 7 Oct 2026

Spatially Adaptive Computation Time for Residual Networks

arXiv 1612.02297 ↗First posted 7 Dec 2016cs.CV cs.LGcited by 118

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 17; 2023: 28; 2024: 12; 2025: 14; 2026: 8.

118 papers.

Sort:

By area:

  1. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  2. 2021Dynamic Neural Networks: A Surveycited by 405
  3. 2021AdaViT: Adaptive Tokens for Efficient Vision Transformercited by 360
  4. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  5. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  6. 2022Scalable Adaptive Computation for Iterative Generationcited by 190
  7. 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143
  8. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  9. 2021SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Eventscited by 84
  10. 2021Spatially-Adaptive Image Restoration using Distortion-Guided Networkscited by 77
  11. 2021Adaptive Focus for Efficient Video Recognitioncited by 76
  12. 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
38 more
  1. 2021FrameExit: Conditional Early Exiting for Efficient Video Recognitioncited by 59
  2. 2021PnP-DETR: Towards Efficient Visual Analysis with Transformerscited by 52
  3. 2021A Survey on Green Deep Learningcited by 52
  4. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  5. 2023Revisiting Token Pruning for Object Detection and Instance Segmentationcited by 50
  6. 2021AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognitioncited by 48
  7. 2022NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Modelscited by 47
  8. 2024AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruningcited by 43
  9. 2022Glance and Focus Networks for Dynamic Visual Recognitioncited by 41
  10. 2023Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Imagescited by 41
  11. 2021Zero Time Waste: Recycling Predictions in Early Exit Neural Networkscited by 39
  12. 2024MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Maskscited by 39
  13. 2021AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognitioncited by 37
  14. 2021AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognitioncited by 36
  15. 2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
  16. 2022Path Independent Equilibrium Models Can Better Exploit Test-Time Computationcited by 33
  17. 2023Dynamic Perceiver for Efficient Visual Recognitioncited by 33
  18. 2021Skip-Convolutions for Efficient Video Processingcited by 32
  19. 2021Dual-side Sparse Tensor Corecited by 27
  20. 2021Deep Joint Source-Channel Coding for Wireless Image Transmission with Adaptive Rate Controlcited by 26
  21. 2023Latency-aware Unified Dynamic Networks for Efficient Image Recognitioncited by 26
  22. 2022Latency-aware Spatial-wise Dynamic Networkscited by 25
  23. 2021Variable-rate discrete representation learningcited by 24
  24. 2022Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inferencecited by 24
  25. 2021RomeBERT: Robust Training of Multi-Exit BERTcited by 19
  26. 2025HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challengescited by 19
  27. 2021Hard-Attention for Scalable Image Classificationcited by 18
  28. 2021PFA: Privacy-preserving Federated Adaptation for Effective Model Personalizationcited by 18
  29. 2021Anytime Dense Prediction with Confidence Adaptivitycited by 18
  30. 2021Multi-Exit Semantic Segmentation Networkscited by 18
  31. 2022Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routingcited by 18
  32. 2022AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognitioncited by 18
  33. 2024Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategycited by 17
  34. 2022LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Modelscited by 16
  35. 2021VA-RED2: Video Adaptive Redundancy Reductioncited by 15
  36. 2023DynamicDet: A Unified Dynamic Architecture for Object Detectioncited by 15
  37. 2021Automated Deep Learning: Neural Architecture Search Is Not the Endcited by 13
  38. 2023Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformerscited by 13

50 most cited of 118 All 118 (JSON)