Research
Computer Vision
What Makes Training Multi-modal Classification Networks Hard?
June 16, 2020
Abstract
Consider end-to-end training of a multi-modal vs. a unimodal network on a task with multiple input modalities: the multi-modal network receives more information, so it should match or outperform its uni-modal counterpart. In our experiments, however, we observe the opposite: the best uni-modal network often outperforms the multi-modal network. This observation is consistent across different combinations of modalities and on different tasks and benchmarks for video classification.
This paper identifies two main causes for this performance drop: first, multi-modal networks are often prone to overfitting due to their increased capacity. Second, different modalities overfit and generalize at different rates, so training them jointly with a single optimization strategy is sub-optimal. We address these two problems with a technique we call Gradient-Blending, which computes an optimal blending of modalities based on their overfitting behaviors. We demonstrate that Gradient Blending outperforms widely-used baselines for avoiding overfitting and achieves state-of-the-art accuracy on various tasks including human action recognition, ego-centric action recognition, and acoustic event detection.
AUTHORS
Written by
Weiyao Wang
Du Tran
Matt Feiszli
Publisher
Conference on Computer Vision and Pattern Recognition (CVPR)
Research Topics
Related Publications
May 26, 2026
Human & Machine Intelligence
Theory
Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
Valentin Wyart, Huy V. Vo, Jean Remi King, Josephine Raugel, Jérémy Rapin, Marc Szafraniec, Max Seitzer, Patrick Labatut, Piotr Bojanowski
May 26, 2026
May 19, 2026
Human & Machine Intelligence
EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data
Alvin W. M. Tan, Nicolas Hamilakis, Manel Khentout, Sho Tsuji, Balázs Kégl, Michael C. Frank, Angel Villar Corrales, Charles-Eric Saint-James, Dongyan Lin, Emmanuel Dupoux, Jiayi Shen, Juan Pino, Mahi Luthra, Martin Gleize, Phillip Rust, Rashel Moritz, Sheila Krogh-Jespersen, Surya Parimi, Tom Fizycki, Vanessa Stark, Yosuke Higuchi, Youssef Benchekroun
May 19, 2026
May 12, 2026
Human & Machine Intelligence
NeuralSet: A High-Performing Python Package for Neuro-AI
Corentin Bel, Linnea Evanson, Julien Gadonneix, Andrea Santos Revilla, Mingfang (Lucy) Zhang, Julie Bonnaire, Charlotte Caucheteux, Alexandre Défossez, Théo Desbordes, Pablo Diego-Simón, Shubh Khanna, Juliette Millet, Pierre Orhan, Saarang Panchavati, Antoine Ratouchniak, Alexis Thual, Hubert Jacob Banville, Jarod Levy, Jean Remi King, Josephine Raugel, Jérémy Rapin, Katelyn Begany, Marlene Careil, Simon Dahan, Sophia Houhamdi, Stéphane d'Ascoli, Teon Brooks, Yohann Benchetrit
May 12, 2026
February 27, 2026
Human & Machine Intelligence
Unified Vision–Language Modeling via Concept Space Alignment
Yifu Qiu, Holger Schwenk, Paul-Ambroise Duquenne
February 27, 2026
June 11, 2019
Computer Vision
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero | Facebook AI Research
Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta, Zhuoyuan Chen, James Pinkerton, Larry Zitnick
June 11, 2019
April 30, 2018
NLP
Computer Vision
Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent | Facebook AI Research
Zhilin Yang, Saizheng Zhang, Jack Urbanek, Will Feng, Alexander H. Miller, Arthur Szlam, Douwe Kiela, Jason Weston
April 30, 2018
October 10, 2016
Speech & Audio
Computer Vision
Polysemous Codes | Facebook AI Research
Matthijs Douze, Hervé Jégou, Florent Perronnin
October 10, 2016
June 18, 2018
Speech & Audio
Computer Vision
Low-shot learning with large-scale diffusion | Facebook AI Research
Matthijs Douze, Arthur Szlam, Bharath Hariharan, Hervé Jégou
June 18, 2018
Help Us Pioneer The Future of AI
We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.
Our approach
Latest news
Foundational models
Meta © 2026