Causality knowledge is vital to building robust AI systems. Deep learning models often perform poorly on tasks that require causal reasoning, which is often derived using some form of commonsense knowledge not immediately available in the input but implicitly inferred by humans. Prior work has unraveled spurious observational biases that models fall prey to in the absence of causality. While language representation models preserve contextual knowledge within learned embeddings, they do not factor in causal relationships during training. By blending causal relationships with the input features to an existing model that performs visual cognition tasks (such as scene understanding, video captioning, video question-answering, etc.), better performance can be achieved owing to the insight causal relationships bring about. Recently, several models have been proposed that have tackled the task of mining causal data from either the visual or textual modality. However, there does not exist widespread research that mines causal relationships by juxtaposing the visual and language modalities. While images offer a rich and easy-to-process resource for us to mine causality knowledge from, videos are denser and consist of naturally time-ordered events. Also, textual information offers details that could be implicit in videos. We propose iReason, a framework that infers visual-semantic commonsense knowledge using both videos and natural language captions. Furthermore, iReason's architecture integrates a causal rationalization module to aid the process of interpretability, error analysis and bias detection. We demonstrate the effectiveness of iReason using a two-pronged comparative analysis with language representation learning models (BERT, GPT-2) as well as current state-of-the-art multimodal causality models.
相關內容
Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills. In this work we propose a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell. We assess the model's performance on two tasks that require different reasoning skills: Abductive Natural Language Inference and Counterfactual Invariance Prediction as a new task. We show that our proposed model improves performance over strong state-of-the-art models (i.e., RoBERTa) across both reasoning tasks. Notably we are, to the best of our knowledge, the first to demonstrate that a model that learns to perform counterfactual reasoning helps predicting the best explanation in an abductive reasoning task. We validate the robustness of the model's reasoning capabilities by perturbing the knowledge and provide qualitative analysis on the model's knowledge incorporation capabilities.
Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Besides, most methods adopt frame-level inter-object features and ambiguous descriptions during training, which is difficult for learning the vision-language relationships. Without associating the transition trajectories, these image-based methods cannot understand the activities with visual features. We propose a novel task, named object-oriented video captioning, which focuses on understanding the videos in object-level. We re-annotate the object-sentence pairs for more effective cross-modal learning. Thereafter, we design the video-based object-oriented video captioning (OVC)-Net to reliably analyze the activities along time with only visual features and capture the vision-language connections under small datasets stably. To demonstrate the effectiveness, we evaluate the method on the new dataset and compare it with the state-of-the-arts for video captioning. From the experimental results, the OVC-Net exhibits the ability of precisely describing the concurrent objects and their activities in details.
We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine that leverages scene graph structures to create 22M diverse reasoning questions, all come with functional programs that represent their semantics. We use the programs to gain tight control over the answer distribution and present a new tunable smoothing technique to mitigate question biases. Accompanying the dataset is a suite of new metrics that evaluate essential qualities such as consistency, grounding and plausibility. An extensive analysis is performed for baselines as well as state-of-the-art models, providing fine-grained results for different question types and topologies. Whereas a blind LSTM obtains mere 42.1%, and strong VQA models achieve 54.1%, human performance tops at 89.3%, offering ample opportunity for new research to explore. We strongly hope GQA will provide an enabling resource for the next generation of models with enhanced robustness, improved consistency, and deeper semantic understanding for images and language.
Recent progress has been made in using attention based encoder-decoder framework for image and video captioning. Most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., "gun" and "shooting") and non-visual words (e.g. "the", "a"). However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention. Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of visual captioning. Furthermore, the hierarchy of LSTMs enables more complex representation of visual data, capturing information at different scales. To address these issues, we propose a hierarchical LSTM with adaptive attention (hLSTMat) approach for image and video captioning. Specifically, the proposed framework utilizes the spatial or temporal attention for selecting specific regions or frames to predict the related words, while the adaptive attention is for deciding whether to depend on the visual information or the language context information. Also, a hierarchical LSTMs is designed to simultaneously consider both low-level visual information and high-level language context information to support the caption generation. We initially design our hLSTMat for video captioning task. Then, we further refine it and apply it to image captioning task. To demonstrate the effectiveness of our proposed framework, we test our method on both video and image captioning tasks. Experimental results show that our approach achieves the state-of-the-art performance for most of the evaluation metrics on both tasks. The effect of important components is also well exploited in the ablation study.
Existing attention mechanisms either attend to local image grid or object level features for Visual Question Answering (VQA). Motivated by the observation that questions can relate to both object instances and their parts, we propose a novel attention mechanism that jointly considers reciprocal relationships between the two levels of visual details. The bottom-up attention thus generated is further coalesced with the top-down information to only focus on the scene elements that are most relevant to a given question. Our design hierarchically fuses multi-modal information i.e., language, object- and gird-level features, through an efficient tensor decomposition scheme. The proposed model improves the state-of-the-art single model performances from 67.9% to 68.2% on VQAv1 and from 65.7% to 67.4% on VQAv2, demonstrating a significant boost.
Movies provide us with a mass of visual content as well as attracting stories. Existing methods have illustrated that understanding movie stories through only visual content is still a hard problem. In this paper, for answering questions about movies, we put forward a Layered Memory Network (LMN) that represents frame-level and clip-level movie content by the Static Word Memory module and the Dynamic Subtitle Memory module, respectively. Particularly, we firstly extract words and sentences from the training movie subtitles. Then the hierarchically formed movie representations, which are learned from LMN, not only encode the correspondence between words and visual content inside frames, but also encode the temporal alignment between sentences and frames inside movie clips. We also extend our LMN model into three variant frameworks to illustrate the good extendable capabilities. We conduct extensive experiments on the MovieQA dataset. With only visual content as inputs, LMN with frame-level representation obtains a large performance improvement. When incorporating subtitles into LMN to form the clip-level representation, we achieve the state-of-the-art performance on the online evaluation task of 'Video+Subtitles'. The good performance successfully demonstrates that the proposed framework of LMN is effective and the hierarchically formed movie representations have good potential for the applications of movie question answering.
We propose a novel method capable of retrieving clips from untrimmed videos based on natural language queries. This cross-modal retrieval task plays a key role in visual-semantic understanding, and requires localizing clips in time and computing their similarity to the query sentence. Current methods generate sentence and video embeddings and then compare them using a late fusion approach, but this ignores the word order in queries and prevents more fine-grained comparisons. Motivated by the need for fine-grained multi-modal feature fusion, we propose a novel early fusion embedding approach that combines video and language information at the word level. Furthermore, we use the inverse task of dense video captioning as a side-task to improve the learned embedding. Our full model combines these components with an efficient proposal pipeline that performs accurate localization of potential video clips. We present a comprehensive experimental validation on two large-scale text-to-clip datasets (Charades-STA and DiDeMo) and attain state-of-the-art retrieval results with our model.
The collaborative reasoning for understanding each image-question pair is very critical but under-explored for an interpretable Visual Question Answering (VQA) system. Although very recent works also tried the explicit compositional processes to assemble multiple sub-tasks embedded in the questions, their models heavily rely on the annotations or hand-crafted rules to obtain valid reasoning layout, leading to either heavy labor or poor performance on composition reasoning. In this paper, to enable global context reasoning for better aligning image and language domains in diverse and unrestricted cases, we propose a novel reasoning network called Adversarial Composition Modular Network (ACMN). This network comprises of two collaborative modules: i) an adversarial attention module to exploit the local visual evidence for each word parsed from the question; ii) a residual composition module to compose the previously mined evidence. Given a dependency parse tree for each question, the adversarial attention module progressively discovers salient regions of one word by densely combining regions of child word nodes in an adversarial manner. Then residual composition module merges the hidden representations of an arbitrary number of children through sum pooling and residual connection. Our ACMN is thus capable of building an interpretable VQA system that gradually dives the image cues following a question-driven reasoning route and makes global reasoning by incorporating the learned knowledge of all attention modules in a principled manner. Experiments on relational datasets demonstrate the superiority of our ACMN and visualization results show the explainable capability of our reasoning system.
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
Visual question answering requires high-order reasoning about an image, which is a fundamental capability needed by machine systems to follow complex directives. Recently, modular networks have been shown to be an effective framework for performing visual reasoning tasks. While modular networks were initially designed with a degree of model transparency, their performance on complex visual reasoning benchmarks was lacking. Current state-of-the-art approaches do not provide an effective mechanism for understanding the reasoning process. In this paper, we close the performance gap between interpretable models and state-of-the-art visual reasoning methods. We propose a set of visual-reasoning primitives which, when composed, manifest as a model capable of performing complex reasoning tasks in an explicitly-interpretable manner. The fidelity and interpretability of the primitives' outputs enable an unparalleled ability to diagnose the strengths and weaknesses of the resulting model. Critically, we show that these primitives are highly performant, achieving state-of-the-art accuracy of 99.1% on the CLEVR dataset. We also show that our model is able to effectively learn generalized representations when provided a small amount of data containing novel object attributes. Using the CoGenT generalization task, we show more than a 20 percentage point improvement over the current state of the art.
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191