mlsanityData to 14 Oct 2026

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration

arXiv 2311.15335 ↗First posted 26 Nov 2023cs.LG cs.AI cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Active Visual Exploration (AVE) optimizes the utilization of robotic resources in real-world scenarios by sequentially selecting the most informative observations. However, modern methods require a high computational budget due to processing the same observations multiple times through the autoencoder transformers. As a remedy, we introduce a novel approach to AVE called TOken REcycling (TORE). It divides the encoder into extractor and aggregator components. The extractor processes each observation separately, enabling the reuse of tokens passed to the aggregator. Moreover, to further reduce the computations, we decrease the decoder to only one block. Through extensive experiments, we demonstrate that TORE outperforms state-of-the-art methods while reducing computational overhead by up to 90%.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 26 Nov 2023.

Builds on

30 of 44 references.

References · 30

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2020Longformer: The Long-Document Transformercited by 3,413
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  8. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 864
  9. 2022Continual Test-Time Domain Adaptationcited by 525
  10. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 449
  11. 2019Transfusion: Understanding Transfer Learning for Medical Imagingcited by 368
  12. 2021AdaViT: Adaptive Tokens for Efficient Vision Transformercited by 362
18 more
  1. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 241
  2. 2019Star-Transformercited by 94
  3. 2023Sensitivity-Aware Visual Parameter-Efficient Fine-Tuningcited by 74
  4. 2020An Exploration of Embodied Visual Explorationcited by 58
  5. 2022Glance and Focus Networks for Dynamic Visual Recognitioncited by 41
  6. 2021Zero Time Waste: Recycling Predictions in Early Exit Neural Networkscited by 39
  7. 2017Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Taskscited by 38
  8. 2020Test-time Unsupervised Domain Adaptationcited by 37
  9. 2022Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningcited by 33
  10. 2023ICICLE: Interpretable Class Incremental Continual Learningcited by 24
  11. 2017Combining Weakly and Webly Supervised Learning for Classifying Food Imagescited by 17
  12. 2023Active Visual Exploration Based on Attention-Map Entropycited by 13
  13. 2022Consistency driven Sequential Transformers Attention Model for Partially Observable Scenescited by 11
  14. 2020Attend and Segment: Attention Guided Active Semantic Segmentationcited by 9
  15. 2021Glimpse-Attend-and-Explore: Self-Attention for Active Visual Explorationcited by 9
  16. 2021MisConv: Convolutional Neural Networks for Missing Datacited by 4
  17. 2022Aerial View Localization with Reinforcement Learning: Towards Emulating Search-and-Rescuecited by 4
  18. 2021Visual Attention in Imaginative Agentscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026CanViT: Toward Active-Vision Foundation Modelscited by 1
  2. 2026HAViT: Historical Attention Vision Transformercited by 0