FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers
FORGE introduces a forward-only test-time adaptation method for convolutional vision models deployed on microcontrollers in a quantization-friendly, inference-only setting. Because integer deployment fuses batch-normalization layers into convolutions, it destroys the statistics that normalization-based adaptation needs. FORGE restores adaptation by re-normalizing each folded convolution's per-channel outputs to clean training statistics using only forward-pass estimates. It recovers most of TENT's accuracy gain (+20.9 vs +24.9 points), needs just 3 of 21 layers to capture 93% of the benefit, works with single-sample streaming, and costs only 8.3 mJ / 21.9 ms on an ESP32-S3.
-->
[Submitted on 1 Sep 2026]
Title:FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers
View a PDF of the paper titled FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers, by Muhammad Rehan and 3 other authors
View PDF HTML (experimental)
Abstract:Vision models deployed on microcontrollers (MCUs) are quantized to integer-only arithmetic and run in inference-only runtimes that do not carry the machinery backpropagation needs: the standard tool for adapting a model to the distribution shift (sensor noise, blur, lighting) it meets in the field. Existing forward-only test-time adaptation (TTA) methods either run only on server- or edge-GPU-class models (not true microcontroller integer execution), or require the batch-normalization (BN) layers that integer deployment fuses away. We present a forward-only TTA method that operates on deployed, BN-folded, integer-only convolutional networks. The key observation is that fusing BN into the preceding convolution, a mandatory step for integer inference, destroys the statistics that normalization-based adaptation relies on. We restore adaptation by re-normalizing each folded convolution's per-channel output to its clean training statistics, using only forward-pass estimates. The method (i) recovers most of gradient-based TENT's accuracy gain (+20.9 vs. +24.9 points) and matches forward-only BN adaptation, while being the only method that runs on a folded integer-only model; (ii) needs to adapt only 3 of 21 layers (selected without seeing the test corruptions) to recover 93% of the benefit; (iii) survives single-sample streaming with a batch-size-scaled momentum; and (iv) generalizes across three datasets (up to 200 classes) and two architectures. We validate bit-exact int8 convolution execution and deploy on an ESP32-S3, where, measured with a Nordic PPK2 power profiler, the forward-only adaptation (a lightweight fp32 recalibration around the int8 convolutions) costs only 8.3 mJ (6.8% of inference energy) and 21.9 ms on the deployed SIMD-optimized model: forward-only adaptation is cheap on a real microcontroller.
Comments: 16 pages, 5 figures, 9 tables. Published in Transactions on Machine Learning Research (2026). OpenReview: this https URL. Code and checkpoints: this https URL
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Hardware Architecture (cs.AR); Machine Learning (cs.LG)
ACM classes: I.2.6; I.5.4; C.3
Cite as: arXiv:2609.01683 [cs.CV]
(or arXiv:2609.01683v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.01683
arXiv-issued DOI via DataCite (pending registration)
Journal reference: Transactions on Machine Learning Research, 2026
Submission history
From: Muhammad Rehan [view email] [v1] Tue, 1 Sep 2026 13:59:28 UTC (168 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers, by Muhammad Rehan and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-09
Change to browse by:
cs cs.AR cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)