For a long time the ability to solve abstract reasoning tasks was considered one of the hallmarks of human intelligence. Recent advances in application of deep learning (DL) methods led, as in many other domains, to surpassing human abstract reasoning performance, specifically in the most popular type of such problems - the Raven's Progressive Matrices (RPMs). While the efficacy of DL systems is indeed impressive, the way they approach the RPMs is very different from that of humans. State-of-the-art systems solving RPMs rely on massive pattern-based training and sometimes on exploiting biases in the dataset, whereas humans concentrate on identification of the rules / concepts underlying the RPM (or generally a visual reasoning task) to be solved. Motivated by this cognitive difference, this work aims at combining DL with human way of solving RPMs and getting the best of both worlds. Specifically, we cast the problem of solving RPMs into multi-label classification framework where each RPM is viewed as a multi-label data point, with labels determined by the set of abstract rules underlying the RPM. For efficient training of the system we introduce a generalisation of the Noise Contrastive Estimation algorithm to the case of multi-label samples. Furthermore, we propose a new sparse rule encoding scheme for RPMs which, besides the new training algorithm, is the key factor contributing to the state-of-the-art performance. The proposed approach is evaluated on two most popular benchmark datasets (Balanced-RAVEN and PGM) and on both of them demonstrates an advantage over the current state-of-the-art results. Contrary to applications of contrastive learning methods reported in other domains, the state-of-the-art performance reported in the paper is achieved with no need for large batch sizes or strong data augmentation.
Existing Visual Question Answering (VQA) models are often fragile and sensitive to input variations. In this paper, we propose a novel approach to address this issue based on modular networks, which creates two questions related by linguistic perturbations and regularizes the visual reasoning process between them to be consistent during training. We show that our framework markedly improves consistency and generalization ability, demonstrating the value of controlled linguistic perturbations as a useful and currently underutilized training and regularization tool for VQA models. We also present VQA Perturbed Pairings (VQA P2), a new, low-cost benchmark and augmentation pipeline to create controllable linguistic variations of VQA questions. Our benchmark uniquely draws from large-scale linguistic resources, avoiding human annotation effort while maintaining data quality compared to generative approaches. We benchmark existing VQA models using VQA P2 and provide robustness analysis on each type of linguistic variation.
This paper defines a new visual reasoning paradigm by introducing an important factor, i.e.~transformation. The motivation comes from the fact that most existing visual reasoning tasks, such as CLEVR in VQA, are solely defined to test how well the machine understands the concepts and relations within static settings, like one image. We argue that this kind of \textbf{state driven visual reasoning} approach has limitations in reflecting whether the machine has the ability to infer the dynamics between different states, which has been shown as important as state-level reasoning for human cognition in Piaget's theory. To tackle this problem, we propose a novel \textbf{transformation driven visual reasoning} task. Given both the initial and final states, the target is to infer the corresponding single-step or multi-step transformation, represented as a triplet (object, attribute, value) or a sequence of triplets, respectively. Following this definition, a new dataset namely TRANCE is constructed on the basis of CLEVR, including three levels of settings, i.e.~Basic (single-step transformation), Event (multi-step transformation), and View (multi-step transformation with variant views). Experimental results show that the state-of-the-art visual reasoning models perform well on Basic, but are still far from human-level intelligence on Event and View. We believe the proposed new paradigm will boost the development of machine visual reasoning. More advanced methods and real data need to be investigated in this direction. The resource of TVR is available at https://hongxin2019.github.io/TVR.
We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; and achieve an interpretable model via working on the induced symbolic concept space. To this end, we first design a new framework named object-centric compositional attention model (OCCAM) to perform the visual reasoning task with object-level visual features. Then, we come up with a method to induce concepts of objects and relations using clues from the attention patterns between objects' visual features and question words. Finally, we achieve a higher level of interpretability by imposing OCCAM on the objects represented in the induced symbolic concept space. Our model design makes this an easy adaption via first predicting the concepts of objects and relations and then projecting the predicted concepts back to the visual feature space so the compositional reasoning module can process normally. Experiments on the CLEVR and GQA datasets demonstrate: 1) our OCCAM achieves a new state of the art without human-annotated functional programs; 2) our induced concepts are both accurate and sufficient as OCCAM achieves an on-par performance on objects represented either in visual features or in the induced symbolic concept space.
Natural language rationales could provide intuitive, higher-level explanations that are easily understandable by humans, complementing the more broadly studied lower-level explanations based on gradients or attention weights. We present the first study focused on generating natural language rationales across several complex visual reasoning tasks: visual commonsense reasoning, visual-textual entailment, and visual question answering. The key challenge of accurate rationalization is comprehensive image understanding at all levels: not just their explicit content at the pixel level, but their contextual contents at the semantic and pragmatic levels. We present Rationale^VT Transformer, an integrated model that learns to generate free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs. Our experiments show that the base pretrained language model benefits from visual adaptation and that free-text rationalization is a promising research direction to complement model interpretability for complex visual-textual reasoning tasks.
Identifying metaphors in text is very challenging and requires comprehending the underlying comparison. The automation of this cognitive process has gained wide attention lately. However, the majority of existing approaches concentrate on word-level identification by treating the task as either single-word classification or sequential labelling without explicitly modelling the interaction between the metaphor components. On the other hand, while existing relation-level approaches implicitly model this interaction, they ignore the context where the metaphor occurs. In this work, we address these limitations by introducing a novel architecture for identifying relation-level metaphoric expressions of certain grammatical relations based on contextual modulation. In a methodology inspired by works in visual reasoning, our approach is based on conditioning the neural network computation on the deep contextualised features of the candidate expressions using feature-wise linear modulation. We demonstrate that the proposed architecture achieves state-of-the-art results on benchmark datasets. The proposed methodology is generic and could be applied to other textual classification problems that benefit from contextual interaction.
Humans have an inherent ability to learn novel concepts from only a few samples and generalize these concepts to different situations. Even though today's machine learning models excel with a plethora of training data on standard recognition tasks, a considerable gap exists between machine-level pattern recognition and human-level concept learning. To narrow this gap, the Bongard problems (BPs) were introduced as an inspirational challenge for visual cognition in intelligent systems. Despite new advances in representation learning and learning to learn, BPs remain a daunting challenge for modern AI. Inspired by the original one hundred BPs, we propose a new benchmark Bongard-LOGO for human-level concept learning and reasoning. We develop a program-guided generation technique to produce a large set of human-interpretable visual cognition problems in action-oriented LOGO language. Our benchmark captures three core properties of human cognition: 1) context-dependent perception, in which the same object may have disparate interpretations given different contexts; 2) analogy-making perception, in which some meaningful concepts are traded off for other meaningful concepts; and 3) perception with a few samples but infinite vocabulary. In experiments, we show that the state-of-the-art deep learning methods perform substantially worse than human subjects, implying that they fail to capture core human cognition properties. Finally, we discuss research directions towards a general architecture for visual reasoning to tackle this benchmark.
The CLEVR dataset has been used extensively in language grounded visual reasoning in Machine Learning (ML) and Natural Language Processing (NLP) domains. We present a graph parser library for CLEVR, that provides functionalities for object-centric attributes and relationships extraction, and construction of structural graph representations for dual modalities. Structural order-invariant representations enable geometric learning and can aid in downstream tasks like language grounding to vision, robotics, compositionality, interpretability, and computational grammar construction. We provide three extensible main components - parser, embedder, and visualizer that can be tailored to suit specific learning setups. We also provide out-of-the-box functionality for seamless integration with popular deep graph neural network (GNN) libraries. Additionally, we discuss downstream usage and applications of the library, and how it accelerates research for the NLP research community.
Visualizing very large matrices involves many formidable problems. Various popular solutions to these problems involve sampling, clustering, projection, or feature selection to reduce the size and complexity of the original task. An important aspect of these methods is how to preserve relative distances between points in the higher-dimensional space after reducing rows and columns to fit in a lower dimensional space. This aspect is important because conclusions based on faulty visual reasoning can be harmful. Judging dissimilar points as similar or similar points as dissimilar on the basis of a visualization can lead to false conclusions. To ameliorate this bias and to make visualizations of very large datasets feasible, we introduce two new algorithms that respectively select a subset of rows and columns of a rectangular matrix. This selection is designed to preserve relative distances as closely as possible. We compare our matrix sketch to more traditional alternatives on a variety of artificial and real datasets.
Learning long-term dynamics models is the key to understanding physical common sense. Most existing approaches on learning dynamics from visual input sidestep long-term predictions by resorting to rapid re-planning with short-term models. This not only requires such models to be super accurate but also limits them only to tasks where an agent can continuously obtain feedback and take action at each step until completion. In this paper, we aim to leverage the ideas from success stories in visual recognition tasks to build object representations that can capture inter-object and object-environment interactions over a long-range. To this end, we propose Region Proposal Interaction Networks (RPIN), which reason about each object's trajectory in a latent region-proposal feature space. Thanks to the simple yet effective object representation, our approach outperforms prior methods by a significant margin both in terms of prediction quality and their ability to plan for downstream tasks, and also generalize well to novel environments. Code, pre-trained models, and more visualization results are available at https://haozhi.io/RPIN.
Generating natural language descriptions for videos, i.e., video captioning, essentially requires step-by-step reasoning along the generation process. For example, to generate the sentence "a man is shooting a basketball", we need to first locate and describe the subject "man", next reason out the man is "shooting", then describe the object "basketball" of shooting. However, existing visual reasoning methods designed for visual question answering are not appropriate to video captioning, for it requires more complex visual reasoning on videos over both space and time, and dynamic module composition along the generation process. In this paper, we propose a novel visual reasoning approach for video captioning, named Reasoning Module Networks (RMN), to equip the existing encoder-decoder framework with the above reasoning capacity. Specifically, our RMN employs 1) three sophisticated spatio-temporal reasoning modules, and 2) a dynamic and discrete module selector trained by a linguistic loss with a Gumbel approximation. Extensive experiments on MSVD and MSR-VTT datasets demonstrate the proposed RMN outperforms the state-of-the-art methods while providing an explicit and explainable generation process. Our code is available at https://github.com/tgc1997/RMN.
Physical reasoning requires forward prediction: the ability to forecast what will happen next given some initial world state. We study the performance of state-of-the-art forward-prediction models in the complex physical-reasoning tasks of the PHYRE benchmark. We do so by incorporating models that operate on object or pixel-based representations of the world into simple physical-reasoning agents. We find that forward-prediction models can improve physical-reasoning performance, particularly on complex tasks that involve many objects. However, we also find that these improvements are contingent on the test tasks being small variations of train tasks, and that generalization to completely new task templates is challenging. Surprisingly, we observe that forward predictors with better pixel accuracy do not necessarily lead to better physical-reasoning performance.Nevertheless, our best models set a new state-of-the-art on the PHYRE benchmark.
We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; followed by (ii) task-specific adversarial finetuning. Instead of adding adversarial perturbations on image pixels and textual tokens, we propose to perform adversarial training in the embedding space of each modality. To enable large-scale training, we adopt the "free" adversarial training strategy, and combine it with KL-divergence-based regularization to promote higher invariance in the embedding space. We apply VILLA to current best-performing V+L models, and achieve new state of the art on a wide range of tasks, including Visual Question Answering, Visual Commonsense Reasoning, Image-Text Retrieval, Referring Expression Comprehension, Visual Entailment, and NLVR2.
In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above. SMA first uses a structural graph representation to encode the object-object, object-text and text-text relationships appearing in the image, and then designs a multimodal graph attention network to reason over it. Finally, the outputs from the above modules are processed by a global-local attentional answering module to produce an answer splicing together tokens from both OCR and general vocabulary iteratively by following M4C. Our proposed model outperforms the SoTA models on TextVQA dataset and two tasks of ST-VQA dataset among all models except pre-training based TAP. Demonstrating strong reasoning ability, it also won first place in TextVQA Challenge 2020. We extensively test different OCR methods on several reasoning models and investigate the impact of gradually increased OCR performance on TextVQA benchmark. With better OCR results, different models share dramatic improvement over the VQA accuracy, but our model benefits most blessed by strong textual-visual reasoning ability. To grant our method an upper bound and make a fair testing base available for further works, we also provide human-annotated ground-truth OCR annotations for the TextVQA dataset, which were not given in the original release. The code and ground-truth OCR annotations for the TextVQA dataset are available at https://github.com/ChenyuGAO-CS/SMA
This work deals with the challenge of learning and reasoning over language and vision data for the related downstream tasks such as visual question answering (VQA) and natural language for visual reasoning (NLVR). We design a novel cross-modality relevance module that is used in an end-to-end framework to learn the relevance representation between components of various input modalities under the supervision of a target task, which is more generalizable to unobserved data compared to merely reshaping the original representation space. In addition to modeling the relevance between the textual entities and visual entities, we model the higher-order relevance between entity relations in the text and object relations in the image. Our proposed approach shows competitive performance on two different language and vision tasks using public benchmarks and improves the state-of-the-art published results. The learned alignments of input spaces and their relevance representations by NLVR task boost the training efficiency of VQA task.
As a comprehensive indicator of mathematical thinking and intelligence, the number sense (Dehaene 2011) bridges the induction of symbolic concepts and the competence of problem-solving. To endow such a crucial cognitive ability to machine intelligence, we propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG). These visual arithmetic problems are in the form of geometric figures: each problem has a set of geometric shapes as its context and embedded number symbols. Solving such problems is not trivial; the machine not only has to recognize the number, but also to interpret the number with its contexts, shapes, and relations (e.g., symmetry) together with proper operations. We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task. Comprehensive experiments show that current neural-network-based models still struggle to understand number concepts and relational operations. We show that a simple brute-force search algorithm could work out some of the problems without context information. Crucially, taking geometric context into account by an additional perception module would provide a sharp performance gain with fewer search steps. Altogether, we call for attention in fusing the classic search-based algorithms with modern neural networks to discover the essential number concepts in future research.
This paper presents a novel attention-based algorithm for achieving adaptive computation called DACT, which, unlike existing ones, is end-to-end differentiable. Our method can be used in conjunction with many networks; in particular, we study its application to the widely known MAC architecture, obtaining a significant reduction in the number of recurrent steps needed to achieve similar accuracies, therefore improving its performance to computation ratio. Furthermore, we show that by increasing the maximum number of steps used, we surpass the accuracy of even our best non-adaptive MAC in the CLEVR dataset, demonstrating that our approach is able to control the number of steps without significant loss of performance. Additional advantages provided by our approach include considerably improving interpretability by discarding useless steps and providing more insights into the underlying reasoning process. Finally, we present adaptive computation as an equivalent to an ensemble of models, similar to a mixture of expert formulation. Both the code and the configuration files for our experiments are made available to support further research in this area.
With the rise of machines to human-level performance in complex recognition tasks, a growing amount of work is directed towards comparing information processing in humans and machines. These studies are an exciting chance to learn about one system by studying the other. Here, we propose ideas on how to design, conduct and interpret experiments such that they adequately support the investigation of mechanisms when comparing human and machine perception. We demonstrate and apply these ideas through three case studies. The first case study shows how human bias can affect how we interpret results, and that several analytic tools can help to overcome this human reference point. In the second case study, we highlight the difference between necessary and sufficient mechanisms in visual reasoning tasks. Thereby, we show that contrary to previous suggestions, feedback mechanisms might not be necessary for the tasks in question. The third case study highlights the importance of aligning experimental conditions. We find that a previously-observed difference in object recognition does not hold when adapting the experiment to make conditions more equitable between humans and machines. In presenting a checklist for comparative studies of visual reasoning in humans and machines, we hope to highlight how to overcome potential pitfalls in design or inference.
Scene Graph Generation (SGG) aims to extract entities, predicates and their semantic structure from images, enabling deep understanding of visual content, with many applications such as visual reasoning and image retrieval. Nevertheless, existing SGG methods require millions of manually annotated bounding boxes for training, and are computationally inefficient, as they exhaustively process all pairs of object proposals to detect predicates. In this paper, we address those two limitations by first proposing a generalized formulation of SGG, namely Visual Semantic Parsing, which disentangles entity and predicate recognition, and enables sub-quadratic performance. Then we propose the Visual Semantic Parsing Network, VSPNet, based on a dynamic, attention-based, bipartite message passing framework that jointly infers graph nodes and edges through an iterative process. Additionally, we propose the first graph-based weakly supervised learning framework, based on a novel graph alignment algorithm, which enables training without bounding box annotations. Through extensive experiments, we show that VSPNet outperforms weakly supervised baselines significantly and approaches fully supervised performance, while being several times faster. We publicly release the source code of our method.
Current home appliances are capable to execute a limited number of voice commands such as turning devices on or off, adjusting music volume or light conditions. Recent progress in machine reasoning gives an opportunity to develop new types of conversational user interfaces for home appliances. In this paper, we apply state-of-the-art visual reasoning model and demonstrate that it is feasible to ask a smart fridge about its contents and various properties of the food with close-to-natural conversation experience. Our visual reasoning model answers user questions about existence, count, category and freshness of each product by analyzing photos made by the image sensor inside the smart fridge. Users may chat with their fridge using off-the-shelf phone messenger while being away from home, for example, when shopping in the supermarket. We generate a visually realistic synthetic dataset to train machine learning reasoning model that achieves 95% answer accuracy on test data. We present the results of initial user tests and discuss how we modify distribution of generated questions for model training based on human-in-the-loop guidance. We open source code for the whole system including dataset generation, reasoning model and demonstration scripts.