Knowing When to Quit: Selective Cascaded Regression with Patch Attention for Real-Time Face Alignment

2021-08-01 · Gil Shapira, Noga Levy, Ishay Goldin, Roy J. Jevnisek

Facial landmarks (FLM) estimation is a critical component in many face-related applications. In this work, we aim to optimize for both accuracy and speed and explore the trade-off between them. Our key observation is that not all faces are created equal. Frontal faces with neutral expressions converge faster than faces with extreme poses or expressions. To differentiate among samples, we train our model to predict the regression error after each iteration. If the current iteration is accurate enough, we stop iterating, saving redundant iterations while keeping the accuracy in check. We also observe that as neighboring patches overlap, we can infer all facial landmarks (FLMs) with only a small number of patches without a major accuracy sacrifice. Architecturally, we offer a multi-scale, patch-based, lightweight feature extractor with a fine-grained local patch attention module, which computes a patch weighting according to the information in the patch itself and enhances the expressive power of the patch features. We analyze the patch attention data to infer where the model is attending when regressing facial landmarks and compare it to face attention in humans. Our model runs in real-time on a mobile device GPU, with 95 Mega Multiply-Add (MMA) operations, outperforming all state-of-the-art methods under 1000 MMA, with a normalized mean error of 8.16 on the 300W challenging dataset.

📄 PDF Abstract BibTeX arXiv:2108.00377

Code (1)

ligaripash/KWtQ-face-alignment 공식 구현 tf

Tasks

Face AlignmentGPUregression

Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

2024-07-25 · JaeHun Jung, Faeze Brahman, Yejin Choi

We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement. We first propose that a reliable evaluation method should not uncritically rely on model preferences for pair…

Chatbot

Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning

2026-04-20 · Hen Davidov, Nachshon Cohen, Oren Kalinsky, Yaron Fairstein 외 arxiv

LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods …

Mathematical Reasoning Reinforcement Learning

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

2026-07-31 · Xinyan Guan, Jiali Zeng, Chunlei Xin, Yaojie Lu 외 hf

Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivations mislead users. We characterize this f…

Reinforcement Learning

Counterfactual Prediction Under Selective Confounding

2023-10-21 · Sohaib Kiani, Jared Barton, Jon Sushinsky, Lynda Heimbach 외

This research addresses the challenge of conducting interpretable causal inference between a binary treatment and its resulting outcome when not all confounders are known. Confounders are factors that have an influence o…

All Causal Inference counterfactual Prediction

Cascaded Neural Networks with Selective Classifiers and its evaluation using Lung X-ray CT Images

2016-11-22 · Masaharu Sakamoto, Hiroki Nakano

Lung nodule detection is a class imbalanced problem because nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority c…

Lung Nodule Detection Sensitivity