Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions. By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks. The model is unified in that (1) it captures all the interactions between the image and the multi-turn dialog using a single-stream Transformer encoder, and (2) it supports both answer ranking and answer generation seamlessly through the same architecture. More crucially, we adapt BERT for the effective fusion of vision and dialog contents via visually grounded training. Without the need of pretraining on external vision-language data, our model yields new state of the art, achieving the top position in both single-model and ensemble settings (74.54 and 75.35 NDCG scores) on the visual dialog leaderboard. Our code and pretrained models are released at https://github.com/salesforce/VD-BERT.
Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context. In this paper, we study how to address two fundamental challenges for this task: (1) reasoning over underlying semantic structures among dialog rounds and (2) identifying several appropriate answers to the given question. To address these challenges, we propose a Sparse Graph Learning (SGL) method to formulate visual dialog as a graph structure learning task. SGL infers inherently sparse dialog structures by incorporating binary and score edges and leveraging a new structural loss function. Next, we introduce a Knowledge Transfer (KT) method that extracts the answer predictions from the teacher model and uses them as pseudo labels. We propose KT to remedy the shortcomings of single ground-truth labels, which severely limit the ability of a model to obtain multiple reasonable answers. As a result, our proposed model significantly improves reasoning capability compared to baseline methods and outperforms the state-of-the-art approaches on the VisDial v1.0 dataset. The source code is available at https://github.com/gicheonkang/SGLKT-VisDial.
Visual Dialog is a vision-language task that requires an AI agent to engage in a conversation with humans grounded in an image. It remains a challenging task since it requires the agent to fully understand a given question before making an appropriate response not only from the textual dialog history, but also from the visually-grounded information. While previous models typically leverage single-hop reasoning or single-channel reasoning to deal with this complex multimodal reasoning task, which is intuitively insufficient. In this paper, we thus propose a novel and more powerful Dual-channel Multi-hop Reasoning Model for Visual Dialog, named DMRM. DMRM synchronously captures information from the dialog history and the image to enrich the semantic representation of the question by exploiting dual-channel reasoning. Specifically, DMRM maintains a dual channel to obtain the question- and history-aware image features and the question- and image-aware dialog history features by a mulit-hop reasoning process in each channel. Additionally, we also design an effective multimodal attention to further enhance the decoder to generate more accurate responses. Experimental results on the VisDial v0.9 and v1.0 datasets demonstrate that the proposed model is effective and outperforms compared models by a significant margin.
Prior work in visual dialog has focused on training deep neural models on VisDial in isolation. Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. We adapt the recently proposed ViLBERT (Lu et al., 2019) model for multi-turn visually-grounded conversations. Our model is pretrained on the Conceptual Captions and Visual Question Answering datasets, and finetuned on VisDial. Our best single model outperforms prior published work (including model ensembles) by more than 1% absolute on NDCG and MRR. Next, we find that additional finetuning using "dense" annotations in VisDial leads to even higher NDCG -- more than 10% over our base model -- but hurts MRR -- more than 17% below our base model! This highlights a trade-off between the two primary metrics -- NDCG and MRR -- which we find is due to dense annotations not correlating well with the original ground-truth answers to questions.
It has been a primary concern in recent studies of vision and language tasks to design an effective attention mechanism dealing with interactions between the two modalities. The Transformer has recently been extended and applied to several bi-modal tasks, yielding promising results. For visual dialog, it becomes necessary to consider interactions between three or more inputs, i.e., an image, a question, and a dialog history, or even its individual dialog components. In this paper, we present a neural architecture named Light-weight Transformer for Many Inputs (LTMI) that can efficiently deal with all the interactions between multiple such inputs in visual dialog. It has a block structure similar to the Transformer and employs the same design of attention computation, whereas it has only a small number of parameters, yet has sufficient representational power for the purpose. Assuming a standard setting of visual dialog, a layer built upon the proposed attention block has less than one-tenth of parameters as compared with its counterpart, a natural Transformer extension. The experimental results on the VisDial datasets validate the effectiveness of the proposed approach, showing improvements of the best NDCG score on the VisDial v1.0 dataset from 57.59 to 60.92 with a single model, from 64.47 to 66.53 with ensemble models, and even to 74.88 with additional finetuning. Our implementation code is available at https://github.com/davidnvq/visdial.
This paper unravels the design tricks adopted by us, the champion team MReaL-BDAI, for Visual Dialog Challenge 2019: two causal principles for improving Visual Dialog (VisDial). By "improving", we mean that they can promote almost every existing VisDial model to the state-of-the-art performance on the leader-board. Such a major improvement is only due to our careful inspection on the causality behind the model and data, finding that the community has overlooked two causalities in VisDial. Intuitively, Principle 1 suggests: we should remove the direct input of the dialog history to the answer model, otherwise a harmful shortcut bias will be introduced; Principle 2 says: there is an unobserved confounder for history, question, and answer, leading to spurious correlations from training data. In particular, to remove the confounder suggested in Principle 2, we propose several causal intervention algorithms, which make the training fundamentally different from the traditional likelihood estimation. Note that the two principles are model-agnostic, so they are applicable in any VisDial model. The code is available at https://github.com/simpleshinobu/visdial-principles.
Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects, relationships or semantics. The key challenge in Visual Dialogue task is thus to learn a more comprehensive and semantic-rich image representation which may have adaptive attentions on the image for variant questions. In this research, we propose a novel model to depict an image from both visual and semantic perspectives. Specifically, the visual view helps capture the appearance-level information, including objects and their relationships, while the semantic view enables the agent to understand high-level visual semantics from the whole image to the local regions. Futhermore, on top of such multi-view image features, we propose a feature selection framework which is able to adaptively capture question-relevant information hierarchically in fine-grained level. The proposed method achieved state-of-the-art results on benchmark Visual Dialogue datasets. More importantly, we can tell which modality (visual or semantic) has more contribution in answering the current question by visualizing the gate values. It gives us insights in understanding of human cognition in Visual Dialogue.
Common grounding is the process of creating, repairing and updating mutual understandings, which is a fundamental aspect of natural language conversation. However, interpreting the process of common grounding is a challenging task, especially under continuous and partially-observable context where complex ambiguity, uncertainty, partial understandings and misunderstandings are introduced. Interpretation becomes even more challenging when we deal with dialogue systems which still have limited capability of natural language understanding and generation. To address this problem, we consider reference resolution as the central subtask of common grounding and propose a new resource to study its intermediate process. Based on a simple and general annotation schema, we collected a total of 40,172 referring expressions in 5,191 dialogues curated from an existing corpus, along with multiple judgements of referent interpretations. We show that our annotation is highly reliable, captures the complexity of common grounding through a natural degree of reasonable disagreements, and allows for more detailed and quantitative analyses of common grounding strategies. Finally, we demonstrate the advantages of our annotation for interpreting, analyzing and improving common grounding in baseline dialogue systems.
Reasoning is an important ability that we learn from a very early age. Yet, reasoning is extremely hard for algorithms. Despite impressive recent progress that has been reported on tasks that necessitate reasoning, such as visual question answering and visual dialog, models often exploit biases in datasets. To develop models with better reasoning abilities, recently, the new visual commonsense reasoning (VCR) task has been introduced. Not only do models have to answer questions, but also do they have to provide a reason for the given answer. The proposed baseline achieved compelling results, leveraging a meticulously designed model composed of LSTM modules and attention nets. Here we show that a much simpler model obtained by ablating and pruning the existing intricate baseline can perform better with half the number of trainable parameters. By associating visual features with attribute information and better text to image grounding, we obtain further improvements for our simpler & effective baseline, TAB-VCR. We show that this approach results in a 5.3%, 4.4% and 6.5% absolute improvement over the previous state-of-the-art on question answering, answer justification and holistic VCR.
Prior work on training generative Visual Dialog models with reinforcement learning(Das et al.) has explored a Qbot-Abot image-guessing game and shown that this 'self-talk' approach can lead to improved performance at the downstream dialog-conditioned image-guessing task. However, this improvement saturates and starts degrading after a few rounds of interaction, and does not lead to a better Visual Dialog model. We find that this is due in part to repeated interactions between Qbot and Abot during self-talk, which are not informative with respect to the image. To improve this, we devise a simple auxiliary objective that incentivizes Qbot to ask diverse questions, thus reducing repetitions and in turn enabling Abot to explore a larger state space during RL ie. be exposed to more visual concepts to talk about, and varied questions to answer. We evaluate our approach via a host of automatic metrics and human studies, and demonstrate that it leads to better dialog, ie. dialog that is more diverse (ie. less repetitive), consistent (ie. has fewer conflicting exchanges), fluent (ie. more human-like),and detailed, while still being comparably image-relevant as prior work and ablations.
We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structures. To obtain a reasonable answer based on the current question and the dialog history, the underlying semantic dependencies between dialog entities are essential. In this paper, we explicitly formalize this task as inference in a graphical model with partially observed nodes and unknown graph structures (relations in dialog). The given dialog entities are viewed as the observed nodes. The answer to a given question is represented by a node with missing value. We first introduce an Expectation Maximization algorithm to infer both the underlying dialog structures and the missing node values (desired answers). Based on this, we proceed to propose a differentiable graph neural network (GNN) solution that approximates this process. Experiment results on the VisDial and VisDial-Q datasets show that our model outperforms comparative methods. It is also observed that our method can infer the underlying dialog structure for better dialog reasoning.
Dialog is an effective way to exchange information, but subtle details and nuances are extremely important. While significant progress has paved a path to address visual dialog with algorithms, details and nuances remain a challenge. Attention mechanisms have demonstrated compelling results to extract details in visual question answering and also provide a convincing framework for visual dialog due to their interpretability and effectiveness. However, the many data utilities that accompany visual dialog challenge existing attention techniques. We address this issue and develop a general attention mechanism for visual dialog which operates on any number of data utilities. To this end, we design a factor graph based attention mechanism which combines any number of utility representations. We illustrate the applicability of the proposed approach on the challenging and recently introduced VisDial datasets, outperforming recent state-of-the-art methods by 1.1% for VisDial0.9 and by 2% for VisDial1.0 on MRR. Our ensemble model improved the MRR score on VisDial1.0 by more than 6%.
Visual Dialog is a multimodal task of answering a sequence of questions grounded in an image, using the conversation history as context. It entails challenges in vision, language, reasoning, and grounding. However, studying these subtasks in isolation on large, real datasets is infeasible as it requires prohibitively-expensive complete annotation of the 'state' of all images and dialogs. We develop CLEVR-Dialog, a large diagnostic dataset for studying multi-round reasoning in visual dialog. Specifically, we construct a dialog grammar that is grounded in the scene graphs of the images from the CLEVR dataset. This combination results in a dataset where all aspects of the visual dialog are fully annotated. In total, CLEVR-Dialog contains 5 instances of 10-round dialogs for about 85k CLEVR images, totaling to 4.25M question-answer pairs. We use CLEVR-Dialog to benchmark performance of standard visual dialog models; in particular, on visual coreference resolution (as a function of the coreference distance). This is the first analysis of its kind for visual dialog models that was not possible without this dataset. We hope the findings from CLEVR-Dialog will help inform the development of future models for visual dialog. Our dataset and code are publicly available.
Text-level discourse parsing aims to unmask how two sentences in the text are related to each other. We propose the task of Visual Discourse Parsing, which requires understanding discourse relations among scenes in a video. Here we use the term scene to refer to a subset of video frames that can better summarize the video. In order to collect a dataset for learning discourse cues from videos, one needs to manually identify the scenes from a large pool of video frames and then annotate the discourse relations between them. This is clearly a time consuming, expensive and tedious task. In this work, we propose an approach to identify discourse cues from the videos without the need to explicitly identify and annotate the scenes. We also present a novel dataset containing 310 videos and the corresponding discourse cues to evaluate our approach. We believe that many of the multi-discipline AI problems such as Visual Dialog and Visual Storytelling would greatly benefit from the use of visual discourse cues.
Visual dialog (VisDial) is a task which requires an AI agent to answer a series of questions grounded in an image. Unlike in visual question answering (VQA), the series of questions should be able to capture a temporal context from a dialog history and exploit visually-grounded information. A problem called visual reference resolution involves these challenges, requiring the agent to resolve ambiguous references in a given question and find the references in a given image. In this paper, we propose Dual Attention Networks (DAN) for visual reference resolution. DAN consists of two kinds of attention networks, REFER and FIND. Specifically, REFER module learns latent relationships between a given question and a dialog history by employing a self-attention mechanism. FIND module takes image features and reference-aware representations (i.e., the output of REFER module) as input, and performs visual grounding via bottom-up attention mechanism. We qualitatively and quantitatively evaluate our model on VisDial v1.0 and v0.9 datasets, showing that DAN outperforms the previous state-of-the-art model by a significant margin.
Answerer in Questioner's Mind (AQM) is an information-theoretic framework that has been recently proposed for task-oriented dialog systems. AQM benefits from asking a question that would maximize the information gain when it is asked. However, due to its intrinsic nature of explicitly calculating the information gain, AQM has a limitation when the solution space is very large. To address this, we propose AQM+ that can deal with a large-scale problem and ask a question that is more coherent to the current context of the dialog. We evaluate our method on GuessWhich, a challenging task-oriented visual dialog problem, where the number of candidate classes is near 10K. Our experimental results and ablation studies show that AQM+ outperforms the state-of-the-art models by a remarkable margin with a reasonable approximation. In particular, the proposed AQM+ reduces more than 60% of error as the dialog proceeds, while the comparative algorithms diminish the error by less than 6%. Based on our results, we argue that AQM+ is a general task-oriented dialog algorithm that can be applied for non-yes-or-no responses.
We characterise some of the quirks and shortcomings in the exploration of Visual Dialogue - a sequential question-answering task where the questions and corresponding answers are related through given visual stimuli. To do so, we develop an embarrassingly simple method based on Canonical Correlation Analysis (CCA) that, on the standard dataset, achieves near state-of-the-art performance on mean rank (MR). In direct contrast to current complex and over-parametrised architectures that are both compute and time intensive, our method ignores the visual stimuli, ignores the sequencing of dialogue, does not need gradients, uses off-the-shelf feature extractors, has at least an order of magnitude fewer parameters, and learns in practically no time. We argue that these results are indicative of issues in current approaches to Visual Dialogue and conduct analyses to highlight implicit dataset biases and effects of over-constrained evaluation metrics. Our code is publicly available.
Visual dialog is a challenging vision-language task, which requires the agent to answer multi-round questions about an image. It typically needs to address two major problems: (1) How to answer visually-grounded questions, which is the core challenge in visual question answering (VQA); (2) How to infer the co-reference between questions and the dialog history. An example of visual co-reference is: pronouns (\eg, ``they'') in the question (\eg, ``Are they on or off?'') are linked with nouns (\eg, ``lamps'') appearing in the dialog history (\eg, ``How many lamps are there?'') and the object grounded in the image. In this work, to resolve the visual co-reference for visual dialog, we propose a novel attention mechanism called Recursive Visual Attention (RvA). Specifically, our dialog agent browses the dialog history until the agent has sufficient confidence in the visual co-reference resolution, and refines the visual attention recursively. The quantitative and qualitative experimental results on the large-scale VisDial v0.9 and v1.0 datasets demonstrate that the proposed RvA not only outperforms the state-of-the-art methods, but also achieves reasonable recursion and interpretable attention maps without additional annotations. The code is available at \url{https://github.com/yuleiniu/rva}.
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue. For such tasks, one successful approach is to condition image-based convolutional network computation on language via Feature-wise Linear Modulation (FiLM) layers, i.e., per-channel scaling and shifting. We propose to generate the parameters of FiLM layers going up the hierarchy of a convolutional network in a multi-hop fashion rather than all at once, as in prior work. By alternating between attending to the language input and generating FiLM layer parameters, this approach is better able to scale to settings with longer input sequences such as dialogue. We demonstrate that multi-hop FiLM generation achieves state-of-the-art for the short input sequence task ReferIt --- on-par with single-hop FiLM generation --- while also significantly outperforming prior state-of-the-art and single-hop FiLM generation on the GuessWhat?! visual dialogue task.
Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and Memory Network structures that leads to an improvement of 7%. The second one is the application of our newly developed TPG methods, which improves the performance additionally by around 5% and, even more importantly, helps produce more convincing utterances.