paper-with-me

Papers

Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition

2024-08-16 · Muhammad Haseeb Aslam, Marco Pedersoli, Alessandro Lameiras Koerich, Eric Granger

Human emotion is a complex phenomenon conveyed and perceived through facial expressions, vocal tones, body language, and physiological signals. Multimodal emotion recognition systems can perform well because they can learn complementary and redundant semantic information from diverse sensors. In real-world scenarios, only a subset of the modalities employed for training may be available at test time. Learning privileged information allows a model to exploit data from additional modalities that are only available during training. SOTA methods for PKD have been proposed to distill information from a teacher model (with privileged modalities) to a student model (without privileged modalities). However, such PKD methods utilize point-to-point matching and do not explicitly capture the relational information. Recently, methods have been proposed to distill the structural information. However, PKD methods based on structural similarity are primarily confined to learning from a single joint teacher representation, which limits their robustness, accuracy, and ability to learn from diverse multimodal sources. In this paper, a multi-teacher PKD (MT-PKDOT) method with self-distillation is introduced to align diverse teacher representations before distilling them to the student. MT-PKDOT employs a structural similarity KD mechanism based on a regularized optimal transport (OT) for distillation. The proposed MT-PKDOT method was validated on the Affwild2 and Biovid datasets. Results indicate that our proposed method can outperform SOTA PKD methods. It improves the visual-only baseline on Biovid data by 5.5%. On the Affwild2 dataset, the proposed method improves 3% and 5% over the visual-only baseline for valence and arousal respectively. Allowing the student to learn from multiple diverse sources is shown to increase the accuracy and implicitly avoids negative transfer to the student model.

📄 PDF Abstract BibTeX arXiv:2408.09035

Code (1)

haseebaslam95/MT-PKDOT 공식 구현 pytorch

Tasks

Emotion RecognitionKnowledge DistillationMultimodal Emotion Recognition

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Learning Using Generated Privileged Information by Text-to-Image Diffusion Models

2023-09-26 · Rafael-Edy Menadil, Mariana-Iuliana Georgescu, Radu Tudor Ionescu

Learning Using Privileged Information is a particular type of knowledge distillation where the teacher model benefits from an additional data representation during training, called privileged information, improving the s…

ClassificationKnowledge Distillationtext-classificationText Classification

On the effectiveness of multimodal privileged knowledge distillation in two vision transformer based diagnostic applications

2025-08-06 · Simon Baur, Alexandra Benova, Emilio Dolgener Cantú, Jackie Ma arxiv

Deploying deep learning models in clinical practice often requires leveraging multiple data modalities, such as images, text, and structured data, to achieve robust and trustworthy decisions. However, not all modalities …

Knowledge Distillation

OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing

2026-06-14 · Zebang Cheng, Shuimu Chen, Boxue Yang, Yuanshen Guan 외 arxiv

Reinforcement learning for multimodal large language models (MLLMs) is often hindered by severe reward sparsity in complex reasoning tasks. This challenge is particularly pronounced in human-centered scenarios involving …

Reinforcement Learning

IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models

2026-07-17 · Xiuyuan Zhu, Ke Lu, Hao Wu, Zijin Du 외 arxiv

Visual grounding with multimodal large language models is commonly formulated as autoregressive coordinate generation, where a model outputs bounding-box coordinates as text given an image and a referring-expression prom…

Instruction FollowingVisual Grounding

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

2026-07-30 · Kangning Zhang, Yixing Li, Shuai Shao, Qingyao Li 외 arxiv

Multimodal on-policy distillation (OPD) transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view teacher. Yet its next-token corrections are source-mixed, combining vis…