mlsanityData to 7 Oct 2026

Asynchronous Perception Machine For Efficient Test-Time-Training

arXiv 2410.20535 ↗First posted 27 Oct 2024cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

In this work, we propose Asynchronous Perception Machine (APM), a computationally-efficient architecture for test-time-training (TTT). APM can process patches of an image one at a time in any order asymmetrically and still encode semantic-awareness in the net. We demonstrate APM's ability to recognize out-of-distribution images without dataset-specific pre-training, augmentation or any-pretext task. APM offers competitive performance over existing TTT approaches. To perform TTT, APM just distills test sample's representation once. APM possesses a unique property: it can learn using just this single representation and starts predicting semantically-aware features. APM demostrates potential applications beyond test-time-training: APM can scale up to a dataset of 2D images and yield semantic-clusterings in a single forward pass. APM also provides first empirical evidence towards validating GLOM's insight, i.e. input percept is a field. Therefore, APM helps us converge towards an implementation which can do both interpolation and perception on a shared-connectionist hardware. Our code is publicly available at this link: https://rajatmodi62.github.io/apm_project_page/.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 51 of its 110 references that are in the map. First posted on arXiv 27 Oct 2024.

Builds on

51 of 110 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  7. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  9. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  10. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  11. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  12. 2020End-to-End Object Detection with Transformerscited by 7,384
38 more
  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  7. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  8. 2020Object-Centric Learning with Slot Attentioncited by 865
  9. 2017Dynamic Routing Between Capsulescited by 689
  10. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  11. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  12. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  13. 2022Continual Test-Time Domain Adaptationcited by 520
  14. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  15. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  16. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  17. 2023Fine-Tuning Language Models with Just Forward Passescited by 337
  18. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  19. 2014One weird trick for parallelizing convolutional neural networkscited by 264
  20. 2022The Forward-Forward Algorithm: Some Preliminary Investigationscited by 262
  21. 2022Test-Time Training with Masked Autoencoderscited by 208
  22. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  23. 2023SUDS: Scalable Urban Dynamic Scenescited by 151
  24. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 150
  25. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  26. 2017The Consciousness Priorcited by 105
  27. 2021Unsupervised Discovery of Object Radiance Fieldscited by 100
  28. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  29. 2019Putting An End to End-to-End: Gradient-Isolated Learning of Representationscited by 85
  30. 2023SoTTA: Robust Test-Time Adaptation on Noisy Data Streamscited by 63
  31. 2024Foundation Models for Video Understanding: A Surveycited by 46
  32. 2022Complex-Valued Autoencoders for Object Discoverycited by 40
  33. 2023Rotating Features for Object Discoverycited by 29
  34. 2023Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedbackcited by 27
  35. 2024Interactive Continual Learning: Fast and Slow Thinkingcited by 23
  36. 2023EZ-CLIP: Efficient Zeroshot Video Action Recognitioncited by 14
  37. 2022Video Action Detection: Analysing Limitations and Challengescited by 12
  38. 2022Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networkscited by 11

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Canonical locks that encode part-whole hierarchiescited by 0
  2. 2026Position Aware Layer Queries for Test Time Training in Vision Language Modelscited by 0