Timezone: »

 
Poster
Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model
Jiasen Lu · Anitha Kannan · Jianwei Yang · Devi Parikh · Dhruv Batra

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #86 #None
in Posters Mon »

We present a novel training framework for neural sequence models, particularly for grounded dialog generation. The standard training paradigm for these models is maximum likelihood estimation (MLE), or minimizing the cross-entropy of the human responses. Across a variety of domains, a recurring problem with MLE trained generative neural dialog models (G) is that they tend to produce 'safe' and generic responses like "I don't know", "I can't tell"). In contrast, discriminative dialog models (D) that are trained to rank a list of candidate human responses outperform their generative counterparts; in terms of automatic metrics, diversity, and informativeness of the responses. However, D is not useful in practice since it can not be deployed to have real conversations with users. Our work aims to achieve the best of both worlds -- the practical usefulness of G and the strong performance of D -- via knowledge transfer from D to G. Our primary contribution is an end-to-end trainable generative visual dialog model, where G receives gradients from D as a perceptual (not adversarial) loss of the sequence sampled from G. We leverage the recently proposed Gumbel-Softmax (GS) approximation to the discrete distribution -- specifically, a RNN is augmented with a sequence of GS samplers, which coupled with the straight-through gradient estimator enables end-to-end differentiability. We also introduce a stronger encoder for visual dialog, and employ a self-attention mechanism for answer encoding along with a metric learning loss to aid D in better capturing semantic similarities in answer responses. Overall, our proposed model outperforms state-of-the-art on the VisDial dataset by a significant margin (2.67% on recall@10). The source code can be downloaded from https://github.com/jiasenlu/visDial.pytorch

Keywords: Visual Question Answering

Author Information

Jiasen Lu (Georgia Tech)
Anitha Kannan
Jianwei Yang (Georgia Tech)
Devi Parikh (Georgia Tech / Facebook AI Research (FAIR))
Dhruv Batra

More from the Same Authors