# Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Tracking

arXiv: https://arxiv.org/abs/2602.16160 · HTML: https://mlsanity.com/paper/2602.16160/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 38 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [Reducing Transformer Depth on Demand with Structured Dropout](https://mlsanity.com/paper/1909.11556/) (2019)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://mlsanity.com/paper/1812.05050/) (2018)
- [Depth-Adaptive Transformer](https://mlsanity.com/paper/1910.10073/) (2019)
- [SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking](https://mlsanity.com/paper/1911.07241/) (2019)
- [MixFormerV2: Efficient Fully Transformer Tracking](https://mlsanity.com/paper/2305.15896/) (2023)
- [CertainNet: Sampling-free Uncertainty Estimation for Object Detection](https://mlsanity.com/paper/2110.01604/) (2021)
- [Lightweight, Uncertainty-Aware Conformalized Visual Odometry](https://mlsanity.com/paper/2303.02207/) (2023)
- [Mutual Information-calibrated Conformal Feature Fusion for Uncertainty-Aware Multimodal 3D Object Detection at the Edge](https://mlsanity.com/paper/2309.09593/) (2023)
- [Exploring Dynamic Transformer for Efficient Object Tracking](https://mlsanity.com/paper/2403.17651/) (2024)

## Built on by (most cited first, 3 of 3)

- [VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation](https://mlsanity.com/paper/2604.25235/) (2026)
- [TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same](https://mlsanity.com/paper/2603.08128/) (2026)
- [Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets](https://mlsanity.com/paper/2606.25760/) (2026)

## Abstract (arXiv)

Transformer-based single-object trackers achieve state-of-the-art accuracy but rely on fixed-depth inference, executing the full encoder--decoder stack for every frame regardless of visual complexity, thereby incurring unnecessary computational cost in long video sequences dominated by temporally coherent frames. We propose UncL-STARK, an architecture-preserving approach that enables dynamic, uncertainty-aware depth adaptation in transformer-based trackers without modifying the underlying network or adding auxiliary heads. The model is fine-tuned to retain predictive robustness at multiple intermediate depths using random-depth training with knowledge distillation, thus enabling safe inference-time truncation. At runtime, we derive a lightweight uncertainty estimate directly from the model's corner localization heatmaps and use it in a feedback-driven policy that selects the encoder and decoder depth for the next frame based on the prediction confidence by exploiting temporal coherence in video. Extensive experiments on GOT-10k and LaSOT demonstrate up to 12% GFLOPs reduction, 8.9% latency reduction, and 10.8% energy savings while maintaining tracking accuracy within 0.2% of the full-depth baseline across both short-term and long-term sequences.