Learning to Generate Grounded Visual Captions without Localization Supervision

European Conference on Computer Vision (ECCV)


When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the model is hallucinating based on priors in the dataset and/or the language model. The most common way of relating image regions with words in caption models is through an attention mechanism over the regions that are used as input to predict the next word. The model must therefore learn to predict the attentional weights without knowing the word it should localize. This is difficult to train without grounding supervision since recurrent models can propagate past information and there is no explicit signal to force the captioning model to properly ground the individual decoded words. In this work, we help the model to achieve this via a novel cyclical training regimen that forces the model to localize each word in the image after the sentence decoder generates it, and then reconstruct the sentence from the localized image region(s) to match the ground-truth. Our proposed framework only requires learning one extra fully-connected layer (the localizer), a layer that can be removed at test time. We show that our model significantly improves grounding accuracy without relying on grounding supervision or introducing extra computation during inference, for both image and video captioning tasks. Code is available at

Related Publications

All Publications

Robust Market Equilibria with Uncertain Preferences

Riley Murray, Christian Kroer, Alex Peysakhovich, Parikshit Shah

AAAI - February 12, 2020

Weak-Attention Suppression For Transformer Based Speech Recognition

Yangyang Shi, Yongqiang Wang, Chunyang Wu, Christian Fuegen, Frank Zhang, Duc Le, Ching-Feng Yeh, Michael L. Seltzer

Interspeech - October 26, 2020

Machine Learning in Compilers: Past, Present, and Future

Hugh Leather, Chris Cummins

FDL - September 14, 2020

Unsupervised Cross-Domain Singing Voice Conversion

Adam Polyak, Lior Wolf, Yossi Adi, Yaniv Taigman

Interspeech - August 8, 2020

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy