Visual Dialog involves "understanding" the dialog history (what has been discussed previously) and the current question (what is asked), in addition to grounding information in the image, to generate the correct response. In this paper, we show that co-attention models which explicitly encode dialog history outperform models that don't, achieving state-of-the-art performance (72 % NDCG on val set). However, we also expose shortcomings of the crowd-sourcing dataset collection procedure by showing that history is indeed only required for a small amount of the data and that the current evaluation metric encourages generic replies. To that end, we propose a challenging subset (VisDialConv) of the VisDial val set and provide a benchmark of 63% NDCG.
Visual dialog is a challenging vision-language task in which a series of questions visually grounded by a given image are answered. To resolve the visual dialog task, a high-level understanding of various multimodal inputs (e.g., question, dialog history, and image) is required. Specifically, it is necessary for an agent to 1) determine the semantic intent of question and 2) align question-relevant textual and visual contents among heterogeneous modality inputs. In this paper, we propose Multi-View Attention Network (MVAN), which leverages multiple views about heterogeneous inputs based on attention mechanisms. MVAN effectively captures the question-relevant information from the dialog history with two complementary modules (i.e., Topic Aggregation and Context Matching), and builds multimodal representations through sequential alignment processes (i.e., Modality Alignment). Experimental results on VisDial v1.0 dataset show the effectiveness of our proposed model, which outperforms the previous state-of-the-art methods with respect to all evaluation metrics.
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 challenging task that requires the comprehension of the semantic dependencies among implicit visual and textual contexts. This task can refer to the relation inference in a graphical model with sparse contexts and unknown graph structure (relation descriptor), and how to model the underlying context-aware relation inference is critical. To this end, we propose a novel Context-Aware Graph (CAG) neural network. Each node in the graph corresponds to a joint semantic feature, including both object-based (visual) and history-related (textual) context representations. The graph structure (relations in dialog) is iteratively updated using an adaptive top-$K$ message passing mechanism. Specifically, in every message passing step, each node selects the most $K$ relevant nodes, and only receives messages from them. Then, after the update, we impose graph attention on all the nodes to get the final graph embedding and infer the answer. In CAG, each node has dynamic relations in the graph (different related $K$ neighbor nodes), and only the most relevant nodes are attributive to the context-aware relational graph inference. Experimental results on VisDial v0.9 and v1.0 datasets show that CAG outperforms comparative methods. Visualization results further validate the interpretability of our method.
The Visual Dialog task requires a model to exploit both image and conversational context information to generate the next response to the dialogue. However, via manual analysis, we find that a large number of conversational questions can be answered by only looking at the image without any access to the context history, while others still need the conversation context to predict the correct answers. We demonstrate that due to this reason, previous joint-modality (history and image) models over-rely on and are more prone to memorizing the dialogue history (e.g., by extracting certain keywords or patterns in the context information), whereas image-only models are more generalizable (because they cannot memorize or extract keywords from history) and perform substantially better at the primary normalized discounted cumulative gain (NDCG) task metric which allows multiple correct answers. Hence, this observation encourages us to explicitly maintain two models, i.e., an image-only model and an image-history joint model, and combine their complementary abilities for a more balanced multimodal model. We present multiple methods for this integration of the two models, via ensemble and consensus dropout fusion with shared parameters. Empirically, our models achieve strong results on the Visual Dialog challenge 2019 (rank 3 on NDCG and high balance across metrics), and substantially outperform the winner of the Visual Dialog challenge 2018 on most metrics.
This manuscript describes our approach for the Visual Dialog Challenge 2018. We use an ensemble of three discriminative models with different encoders and decoders for our final submission. Our best performing model on 'test-std' split achieves the NDCG score of 55.46 and the MRR value of 63.77, securing third position in the challenge.
Vision and language are two fundamental capabilities of human intelligence. Humans routinely perform tasks through the interactions between vision and language, supporting the uniquely human capacity to talk about what they see or hallucinate a picture on a natural-language description. The valid question of how language interacts with vision motivates us researchers to expand the horizons of computer vision area. In particular, "vision to language" is probably one of the most popular topics in the past five years, with a significant growth in both volume of publications and extensive applications, e.g., captioning, visual question answering, visual dialog, language navigation, etc. Such tasks boost visual perception with more comprehensive understanding and diverse linguistic representations. Going beyond the progresses made in "vision to language," language can also contribute to vision understanding and offer new possibilities of visual content creation, i.e., "language to vision." The process performs as a prism through which to create visual content conditioning on the language inputs. This paper reviews the recent advances along these two dimensions: "vision to language" and "language to vision." More concretely, the former mainly focuses on the development of image/video captioning, as well as typical encoder-decoder structures and benchmarks, while the latter summarizes the technologies of visual content creation. The real-world deployment or services of vision and language are elaborated as well.
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.
GuessWhat?! is a visual dialogue task between a guesser and an oracle. The guesser aims to locate an object supposed by the oracle oneself in an image by asking a sequence of Yes/No questions. Asking proper questions with the progress of dialogue is vital for achieving successful final guess. As a result, the progress of dialogue should be properly represented and tracked. Previous models for question generation pay less attention on the representation and tracking of dialogue states, and therefore are prone to asking low quality questions such as repeated questions. This paper proposes visual dialogue state tracking (VDST) based method for question generation. A visual dialogue state is defined as the distribution on objects in the image as well as representations of objects. Representations of objects are updated with the change of the distribution on objects. An object-difference based attention is used to decode new question. The distribution on objects is updated by comparing the question-answer pair and objects. Experimental results on GuessWhat?! dataset show that our model significantly outperforms existing methods and achieves new state-of-the-art performance. It is also noticeable that our model reduces the rate of repeated questions from more than 50% to 21.9% compared with previous state-of-the-art methods.
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.
Vision and language tasks have benefited from attention. There have been a number of different attention models proposed. However, the scale at which attention needs to be applied has not been well examined. Particularly, in this work, we propose a new method Granular Multi-modal Attention, where we aim to particularly address the question of the right granularity at which one needs to attend while solving the Visual Dialog task. The proposed method shows improvement in both image and text attention networks. We then propose a granular Multi-modal Attention network that jointly attends on the image and text granules and shows the best performance. With this work, we observe that obtaining granular attention and doing exhaustive Multi-modal Attention appears to be the best way to attend while solving visual dialog.
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.
Latest addition to the toolbox of human species is Artificial Intelligence(AI). Thus far, AI has made significant progress in low stake low risk scenarios such as playing Go and we are currently in a transition toward medium stake scenarios such as Visual Dialog. In my thesis, I argue that we need to incorporate controlled de-entanglement as first class object to succeed in this transition. I present mathematical analysis from information theory to show that employing stochasticity leads to controlled de-entanglement of relevant factors of variation at various levels. Based on this, I highlight results from initial experiments that depict efficacy of the proposed framework. I conclude this writeup by a roadmap of experiments that show the applicability of this framework to scalability, flexibility and interpretibility.
Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence (seq2seq) framework with the action space being the output vocabulary in the decoder. However, it is difficult to design a reward function that can achieve a balance between learning an effective policy and generating a natural dialog response. This paper proposes a novel framework that alternatively trains a RL policy for image guessing and a supervised seq2seq model to improve dialog generation quality. We evaluate our framework on the GuessWhich task and the framework achieves the state-of-the-art performance in both task completion and dialog quality.