Referring Expression Comprehension Research Articles

A Real-Time Global Inference Network for One-Stage Referring Expression Comprehension.

Referring expression comprehension (REC) is an emerging research topic in computer vision, which refers to the detection of a target region in an image given a test description. Most existing REC methods follow a multistage pipeline, which is computationally expensive and greatly limits the applications of REC. In this article, we propose a one-stage model toward real-time REC, termed real-time global inference network (RealGIN). RealGIN addresses the issues of expression diversity and complexity of REC with two innovative designs: adaptive feature selection (AFS) and Global Attentive ReAsoNing (GARAN). Expression diversity concerns varying expression content, which includes information such as colors, attributes, locations, and fine-grained categories. To address this issue, AFS adaptively fuses features of different semantic levels to tackle the changes in expression content. In contrast, expression complexity concerns the complex relational conditions in expressions that are used to identify the referent. To this end, GARAN uses the textual feature as a pivot to collect expression-aware visual information from all regions and then diffuses this information back to each region, which provides sufficient context for modeling the relational conditions in expressions. On five benchmark datasets, i.e., RefCOCO, RefCOCO+, RefCOCOg, ReferIT, and Flickr30k, the proposed RealGIN outperforms most existing methods and achieves very competitive performances against the most advanced one, i.e., MAttNet. More importantly, under the same hardware, RealGIN can boost the processing speed by 10-20 times over the existing methods.

Multiple Relational Learning Network for Joint Referring Expression Comprehension and Segmentation

Multi-task learning is a successful learning framework which improves the performance of prediction models by leveraging knowledge among related tasks. Referring expression comprehension (REC) and segmentation (RES) are highly relevant tasks, which both are language-guided visual recognition tasks. However, their relations have not yet been fully exploited in previous works. In this paper, a Multiple Relational Learning Network (MRLN) is proposed for multi-task learning of REC and RES. First, a feature-feature interaction learning module is introduced to handle the complicated interactions among features. Moreover, we propose a feature-task dependence learning module, which associates the related features with target tasks. Furthermore, a task-task relationship learning module is designed, which captures the relationships among tasks automatically and guides the REC and RES fine-tuning adaptively. To verify our proposed approach, experiments are conducted on three benchmark datasets, i.e., RefCOCO, RefCOCO+, and RefCOCOg. Extensive experiments demonstrate that the multiple relationships are more appealing since it alleviates the prediction inconsistency issue in multi-task setup. In addition, the experimental results report the significant performance gains of MRLN over most existing methods, i.e., up to 83.46 % for REC and 63.62 % for RES over state-of-the-art methods, which demonstrate the validity and superiority of MRLN.

InterREC: An Interpretable Method for Referring Expression Comprehension

Referring Expression Comprehension (REC) aims to locate the target object in the image according to a referring expression. This is a challenging task owing to the need for understanding both natural language and visual information and interpretable reasoning between them. Most existing implicit reasoning-based REC methods lack interpretability, while explicit reasoning-based REC methods have lower accuracy. To achieve competitive accuracy while providing adequate interpretability, in this work, we propose a novel explicit reasoning-based method named InterREC. First, in order to address the challenge of multi-modal understanding, we design two neural network modules based on text-image representation learning: a Text-Region Matching Module to align objects in the image and noun phrases in the expression, and a Text-Relation Matching Module to align relations between objects in the image and relational phrases in the expression. Additionally, we design a Reasoning Order Tree for handling complex expressions, which can reduce complex expressions to multiple object-relation-object triplets and therefore identify the inference order and reduce the difficulty of reasoning. At the same time, to achieve an interpretable reasoning step, we design a Bayesian Network-based explicit reasoning method. Based on the comparative evaluation on various datasets, our method achieves higher accuracy than existing explicit reasoning-based REC methods, and the visualization results demonstrate the method's high interpretability.

A Proposal-Free One-Stage Framework for Referring Expression Comprehension and Generation via Dense Cross-Attention

Referring Expression Comprehension (REC) and Generation (REG) have become one of the most important tasks in visual reasoning, since it is an essential step for many vision-and-language tasks such as visual question answering or visual dialogue. However, it has not been widely used in many downstream tasks, mainly for the following reasons: 1) mainstream two-stage methods rely on additional annotations or off-the-shelf detectors to generate proposals. It would heavily degrade the generalization ability of models and lead to inevitable error accumulation. 2) Although one-stage strategies for REC have been proposed, these methods have to depend on lots of hyper-parameters (such as anchors) to generate bounding box. In this paper, we present a proposal-free one-stage (PFOS) framework that can directly regress the region-of-interest from the image or generate unambiguous descriptions in an end-to-end manner. Instead of using the dominant two-stage fashion, we take the dense-grid of images as input for a cross-attention transformer that learns multi-modal correspondences. The final bounding box or sentence is directly predicted from the image without the anchor selection or the computation of visual difference. Furthermore, we expand the traditional two-stage listener-speaker framework to jointly train by a one-stage learning paradigm. Our model achieves state-of-the-art performance on both accuracy and speed for comprehension and competitive results for generation.

Scene-Text Oriented Referring Expression Comprehension

Referring expression comprehension (REC) aims to identify and locate a specific object in visual scenes referred to by a natural language expression. Existing studies of REC only focus on basic visual attributes and neglect scene text. Since scene text has the functions of object identification and disambiguation, it is naturally and frequently used to refer to objects. However, existing methods do not explicitly recognize text in images and fail to align scene text mentioned in expressions with the text shown in images, resulting in object localization errors. This study takes the first step toward addressing these limitations. First, we introduce a new task called scene-text oriented referring expression comprehension, which aims to align visual cues and textual semantics of scene text with referring expressions and visual contents. Second, we propose a scene text awareness network that can bridge the gap between texts from two modalities by grounding visual representations of expression-correlated scene texts. Specifically, we propose a correlated text extraction module to solve the problem of lacking semantic understanding, and a correlated region activation module to address the fixed alignment problem and absent alignment problem. These modules ensure that the proposed method focuses on local regions that are most relevant to scene text, thus mitigating the misalignment of scene text with irrelevant regions. Third, to conduct quantitative evaluations, we establish a new benchmark dataset called RefText. Experimental results demonstrate that the proposed method can effectively comprehend scene-text oriented referring expressions and achieves excellent performance.

Rethinking and Improving Feature Pyramids for One-stage Referring Expression Comprehension.

Referring Expression Comprehension (REC) is an important task in the vision-and-language community, since it is an essential step for many cross-modal tasks such as VQA, image retrieval and image caption. To obtain a better trade-off between speed and accuracy, existing researches usually follow a one-stage paradigm, where this task can be considered as a language-conditioned object detection task. Meanwhile, previous one-stage REC frameworks provide many different research perspectives, such as the strategies of fusion, the stage of fusion and the design of detection head. Surprisingly, these works mostly ignore the value of integrating multi-level features and even only apply single-scale features to locate the target. In this paper, we focus on rethinking and improving feature pyramids for one-stage REC. By experimental validations, we first prove that although multi-scale fusion is an effective approach for improving performance, the mature neck structures from object detection (e.g., FPN, BFN and HRFPN) have a limited impact on this task. Further, we visualize the outputs of FPN and find the underlying reason is that these coarse-grained FPN fusion strategies suffer from semantic ambiguity problem. Based on the above insights, we propose a new Language-Guided FPN (LG-FPN) method, which can dynamically allocate and select the fine-grained information by stacking language-gate and union-gate. A large number of contrastive and ablative experiments show that our LG-FPN is an effective and reliable module that can adapt to different visual backbones, fusion strategies and detection heads. Finally, our method achieves state-of-the-art performance on four referring expression datasets.

One for all: One-stage referring expression comprehension with dynamic reasoning

Referring Expression Comprehension (REC) is one of the most important tasks in visual reasoning that requires a model to detect the target object referred by a natural language expression. Among the proposed pipelines, the one-stage Referring Expression Comprehension (OSREC) has become the dominant trend since it merges the region proposal and selection stages. Many state-of-the-art OSREC models adopt a multi-hop reasoning strategy because a sequence of objects is frequently mentioned in a single expression which needs multi-hop reasoning to analyze the semantic relation. However, one unsolved issue of these models is that the number of reasoning steps needs to be pre-defined and fixed before inference, ignoring the varying complexity of expressions. In this paper, we propose a Dynamic Multi-step Reasoning Network, which allows the reasoning steps to be dynamically adjusted based on the reasoning state and expression complexity. Specifically, we adopt a Transformer module to memorize & process the reasoning state and a Reinforcement Learning strategy to dynamically infer the reasoning steps. The work achieves the state-of-the-art performance or significant improvements on several REC datasets, ranging from RefCOCO (+, g) with short expressions, to Ref-Reasoning, a dataset with long and complex compositional expressions.

Understanding Synonymous Referring Expressions via Contrastive Features

Referring expression comprehension aims to localize objects identified by natural language descriptions. This is a challenging task as it requires understanding of both visual and language domains. One nature is that each object can be described by synonymous sentences with paraphrases, and such varieties in languages have critical impact on learning a comprehension model. While prior work usually treats each sentence and attends it to an object separately, we focus on learning a referring expression comprehension model that considers the property in synonymous sentences. To this end, we develop an end-to-end trainable framework to learn contrastive features on the image and object instance levels, where features extracted from synonymous sentences to describe the same object should be closer to each other after mapping to the visual domain. We conduct extensive experiments to evaluate the proposed algorithm on several benchmark datasets, and demonstrate that our method performs favorably against the state-of-the-art approaches. Furthermore, since the varieties in expressions become larger across datasets when they describe objects in different ways, we present the cross-dataset and transfer learning settings to validate the ability of our learned transferable features.

Learning the Dynamics of Visual Relational Reasoning via Reinforced Path Routing

Reasoning is a dynamic process. In cognitive theories, the dynamics of reasoning refers to reasoning states over time after successive state transitions. Modeling the cognitive dynamics is of utmost importance to simulate human reasoning capability. In this paper, we propose to learn the reasoning dynamics of visual relational reasoning by casting it as a path routing task. We present a reinforced path routing method that represents an input image via a structured visual graph and introduces a reinforcement learning based model to explore paths (sequences of nodes) over the graph based on an input sentence to infer reasoning results. By exploring such paths, the proposed method represents reasoning states clearly and characterizes state transitions explicitly to fully model the reasoning dynamics for accurate and transparent visual relational reasoning. Extensive experiments on referring expression comprehension and visual question answering demonstrate the effectiveness of our method.

Bridging the Gap between Expression and Scene Text for Referring Expression Comprehension (Student Abstract)

Referring expression comprehension aims at grounding the object in an image referred to by the expression. Scene text that serves as an identifier has a natural advantage in referring to objects. However, existing methods only consider the text in the expression, but ignore the text in the image, leading to a mismatch. In this paper, we propose a novel model that can recognize the scene text. We assign the extracted scene text to its corresponding visual region and ground the target object guided by expression. Experimental results on two benchmarks demonstrate the effectiveness of our model.

Playing Lottery Tickets with Vision and Language

Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide range of VL tasks. However, the large number of parameters in such models hinders their application in practice. In parallel, work on the lottery ticket hypothesis (LTH) has shown that deep neural networks contain small matching subnetworks that can achieve on par or even better performance than the dense networks when trained in isolation. In this work, we perform the first empirical study to assess whether such trainable subnetworks also exist in pre-trained VL models. We use UNITER as the main testbed (also test on LXMERT and ViLT), and consolidate 7 representative VL tasks for experiments, including visual question answering, visual commonsense reasoning, visual entailment, referring expression comprehension, image-text retrieval, GQA, and NLVR2. Through comprehensive analysis, we summarize our main findings as follows. (i) It is difficult to find subnetworks that strictly match the performance of the full model. However, we can find relaxed winning tickets at 50%-70% sparsity that maintain 99% of the full accuracy. (ii) Subnetworks found by task-specific pruning transfer reasonably well to the other tasks, while those found on the pre-training tasks at 60%/70% sparsity transfer universally, matching 98%/96% of the full accuracy on average over all the tasks. (iii) Besides UNITER, other models such as LXMERT and ViLT can also play lottery tickets. However, the highest sparsity we can achieve for ViLT is far lower than LXMERT and UNITER (30% vs. 70%). (iv) LTH also remains relevant when using other training methods (e.g., adversarial training).

Continual Referring Expression Comprehension via Dual Modular Memorization.

Referring Expression Comprehension (REC) aims to localize an image region of a given object described by a natural-language expression. While promising performance has been demonstrated, existing REC algorithms make a strong assumption that training data feeding into a model are given upfront, which degrades its practicality for real-world scenarios. In this paper, we propose Continual Referring Expression Comprehension (CREC), a new setting for REC, where a model is learning on a stream of incoming tasks. In order to continuously improve the model on sequential tasks without forgetting prior learned knowledge and without repeatedly re-training from a scratch, we propose an effective baseline method named Dual Modular Memorization (DMM), which alleviates the problem of catastrophic forgetting by two memorization modules: Implicit-Memory and Explicit-Memory. Specifically, the former module aims to constrain drastic changes to important parameters learned on old tasks when learning a new task; while the latter module maintains a buffer pool to dynamically select and store representative samples of each seen task for future rehearsal. We create three benchmarks for the new CREC setting, by respectively re-splitting three widely-used REC datasets RefCOCO, RefCOCO+ and RefCOCOg into sequential tasks. Extensive experiments on the constructed benchmarks demonstrate that our DMM method significantly outperforms other alternatives, based on two popular REC backbones. We make the source code and benchmarks publicly available to foster future progress in this field: https://github.com/zackschen/DMM.

Multilevel Attention for Referring Expression Comprehension

Multilevel Attention for Referring Expression Comprehension

Cross-modality synergy network for referring expression comprehension and segmentation

Referring expression comprehension and segmentation aim to locate and segment a referred instance in an image according to a natural language expression. However, existing methods tend to ignore the interaction between visual and language modalities for visual feature learning, and establishing a synergy between the visual and language modalities remains a considerable challenge. To tackle the above problems, we propose a novel end-to-end framework, Cross-Modality Synergy Network (CMS-Net), to address the two tasks jointly. In this work, we propose an attention-aware representation learning module to learn modal representations for both images and expressions. A language self-attention submodule is proposed in this module to learn expression representations by leveraging the intra-modality relations, and a language-guided channel-spatial attention submodule is introduced to obtain the language-aware visual representations under language guidance, which helps the model pay more attention to the referent-relevant regions in the images and relieve background interference. Then, we design a cross-modality synergy module to establish the inter-modality relations for modality fusion. Specifically, a language-visual similarity is obtained at each position of the visual feature map, and the synergy is achieved between the two modalities in both semantic and spatial dimensions. Furthermore, we propose a multi-scale feature fusion module with a selective strategy to aggregate the important information from multi-scale features, yielding target results. We conduct extensive experiments on four challenging benchmarks, and our framework achieves significant performance gains over state-of-the-art methods.

Image Segmentation With Language Referring Expression and Comprehension

Image segmentation with language referring expression can complete object segmentation based on expression text. Existing image segmentation methods show good results on high-performance computers, but most robot systems need real-time and high accuracy. At present, most methods cannot meet these requirements well. Therefore, we propose a high-precision and real-time deep learning network that integrates the two tasks of image segmentation with language referring expression and referring expression comprehension and then treats them as two branches. Specifically, the proposed network first merges the two tasks. The feature maps of different scales extracted by each branch are fed back to the two branches to obtain prediction results. These two tasks promote and restrict each other. Experiments show that our method has better real-time performance and higher accuracy than existing methods.

Referring Expression Comprehension: A Survey of Methods and Datasets

Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been pre-defined, the REC problem only can observe the queries during the test. It is more challenging than a conventional computer vision problem. This task has attracted a lot of attention from both computer vision and natural language processing community, and several lines of work have been proposed, from CNN-RNN model, modular network to complex graph-based model. In this survey, we first examine the state-of-the-art by comparing modern approaches to the problem. We classify methods by their mechanism to encode the visual and textual modalities. In particular, we examine the common approach of joint embedding images and expressions to a common feature space. We also discuss modular architectures and graph-based models that interface with structured graph representation. In the second part of this survey, we review the datasets available for training and evaluating REC approaches. We then group results according to the datasets, backbone models, settings so that they can be fairly compared. Finally, we discuss promising future directions for this field, in particular the compositional referring expression comprehension that requires more reasoning steps to address.

Referring expression comprehension model with matching detection and linguistic feedback

The task of referring expression comprehension (REC) is to localise an image region of a specific object described by a natural language expression, and all existing REC methods assume that the object described by the referring expression must be located in the given image. However, this assumption is not correct in some real applications. For example, a visually impaired user might tell his robot ‘please take the laptop on the table to me’. In fact, the laptop is not on the table anymore. To address this problem, the authors propose a novel REC model to deal with the situation where expression‐image mismatching occurs and explain the mismatching by linguistic feedback. The authors' REC model consists of four modules: the expression parsing module, the entity detection module, the relationship detection module, and the matching detection module. They built a data set called NP‐RefCOCO+ from RefCOCO+ including both positive samples and negative samples. The positive samples are original expression‐image pairs in RefCOCO+. The negative samples are the expression‐image pairs in RefCOCO+, whose expressions are replaced. They evaluate the model on NP‐RefCOCO+ and the experimental results show the advantages of their method for dealing with the problem of expression‐image mismatching.

Interactive Natural Language Grounding via Referring Expression Comprehension and Scene Graph Parsing.

Natural language provides an intuitive and effective interaction interface between human beings and robots. Currently, multiple approaches are presented to address natural language visual grounding for human-robot interaction. However, most of the existing approaches handle the ambiguity of natural language queries and achieve target objects grounding via dialogue systems, which make the interactions cumbersome and time-consuming. In contrast, we address interactive natural language grounding without auxiliary information. Specifically, we first propose a referring expression comprehension network to ground natural referring expressions. The referring expression comprehension network excavates the visual semantics via a visual semantic-aware network, and exploits the rich linguistic contexts in expressions by a language attention network. Furthermore, we combine the referring expression comprehension network with scene graph parsing to achieve unrestricted and complicated natural language grounding. Finally, we validate the performance of the referring expression comprehension network on three public datasets, and we also evaluate the effectiveness of the interactive natural language grounding architecture by conducting extensive natural language query groundings in different household scenarios.