PyTorchKR Papers

최신 논문

총 595편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1908.06354공식 코드 · Papers with Code

A Fast and Accurate One-Stage Approach to Visual Grounding

We propose a simple, fast, and accurate one-stage approach to visual grounding, inspired by the following insight. The performances of existing propose-and-rank two-stage methods are capped by the quality of the region candidates they propose in the first stage --- if none of the candidates could cover the ground truth region, there is no hope in the second stage to rank the right region to the top. To avoid this caveat, we propose a one-stage model that enables end-to-end joint optimization. The main idea is as straightforward as fusing a text query's embedding into the YOLOv3 object detector, augmented by spatial features so as to account for spatial mentions in the query. Despite being simple, this one-stage approach shows great potential in terms of both accuracy and speed for both phrase localization and referring expression comprehension, according to our experiments. Given these results along with careful investigations into some popular region proposals, we advocate for visual grounding a paradigm shift from the conventional two-stage methods to the one-stage framework.

arXiv:1908.04107

Multimodal Unified Attention Networks for Vision-and-Language Interactions

Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use co-attention models to associate each visual object (e.g., image region) with each textual object (e.g., query word). Despite the success of these co-attention models, they only model inter-modal interactions while neglecting intra-modal interactions. Here we propose a general `unified attention' model that simultaneously captures the intra- and inter-modal interactions of multimodal features and outputs their corresponding attended representations. By stacking such unified attention blocks in depth, we obtain the deep Multimodal Unified Attention Network (MUAN), which can seamlessly be applied to the visual question answering (VQA) and visual grounding tasks. We evaluate our MUAN models on two VQA datasets and three visual grounding datasets, and the results show that MUAN achieves top-level performance on both tasks without bells and whistles.

arXiv:1908.02265

ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring expressions, and caption-based image retrieval -- by making only minor additions to the base architecture. We observe significant improvements across tasks compared to existing task-specific models -- achieving state-of-the-art on all four tasks. Our work represents a shift away from learning groundings between vision and language only as part of task training and towards treating visual grounding as a pretrainable and transferable capability.

arXiv:1907.07507

Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe

It has long been speculated that deep neural networks function by discovering a hierarchical set of domain-specific core concepts or patterns, which are further combined to recognize even more elaborate concepts for the classification or other machine learning tasks. Meanwhile disentangling the actual core concepts engrained in the word embeddings (like word2vec or BERT) or deep convolutional image recognition neural networks (like PG-GAN) is difficult and some success there has been achieved only recently. In this paper we propose a novel neural network nonlinearity named Differentiable Disentanglement Filter (DDF) which can be transparently inserted into any existing neural network layer to automatically disentangle the core concepts used by that layer. The DDF probe is inspired by the obscure properties of the hyper-dimensional computing theory. The DDF proof-of-concept implementation is shown to disentangle concepts within the neural 3D scene representation - a task vital for visual grounding of natural language narratives.

arXiv:1907.04355

Transfer Learning from Audio-Visual Grounding to Speech Recognition

Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic features from grounding models that are trained to tell whether a pair of image and speech are semantically correlated, without using any textual transcripts. As semantics of speech are largely determined by its lexical content, grounding models learn to preserve phonetic information while disregarding uncorrelated factors, such as speaker and channel. To study the properties of features distilled from different layers, we use them as input separately to train multiple speech recognition models. Empirical results demonstrate that layers closer to input retain more phonetic information, while following layers exhibit greater invariance to domain shift. Moreover, while most previous studies include training data for speech recognition for feature extractor training, our grounding models are not trained on any of those data, indicating more universal applicability to new domains.

arXiv:1906.03561

Joint Visual Grounding with Language Scene Graphs

Visual grounding is a task to ground referring expressions in images, e.g., localize "the white truck in front of the yellow one". To resolve this task fundamentally, the model should first find out the contextual objects (e.g., the "yellow" truck) and then exploit them to disambiguate the referent from other similar objects by using the attributes and relationships (e.g., "white", "yellow", "in front of"). However, due to the lack of annotations on contextual objects and their relationships, existing methods degenerate the above joint grounding process into a holistic association between the expression and regions, thus suffering from unsatisfactory performance and limited interpretability. In this paper, we alleviate the missing-annotation problem and enable the joint reasoning by leveraging the language scene graph which covers both labeled referent and unlabeled contexts (other objects, attributes, and relationships). Specifically, the language scene graph is a graphical representation where the nodes are objects with attributes and the edges are relationships. We construct a factor graph based on it and then perform marginalization over the graph, such that we can ground both referent and contexts on corresponding image regions to achieve the joint visual grounding (JVG). Experimental results demonstrate that the proposed approach is effective and interpretable, e.g., on three benchmarks, it outperforms the state-of-the-art methods while offers a complete grounding of all the objects mentioned in the referring expression.

arXiv:1906.02890

Visually Grounded Neural Syntax Acquisition

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an approach for learning syntactic representations and structures without any explicit supervision. The model learns by looking at natural images and reading paired captions. VG-NSL generates constituency parse trees of texts, recursively composes representations for constituents, and matches them with images. We define concreteness of constituents by their matching scores with images, and use it to guide the parsing of text. Experiments on the MSCOCO data set show that VG-NSL outperforms various unsupervised parsing approaches that do not use visual grounding, in terms of F1 scores against gold parse trees. We find that VGNSL is much more stable with respect to the choice of random initialization and the amount of training data. We also find that the concreteness acquired by VG-NSL correlates well with a similar measure defined by linguists. Finally, we also apply VG-NSL to multiple languages in the Multi30K data set, showing that our model consistently outperforms prior unsupervised approaches.

arXiv:1906.01784

Learning to Compose and Reason with Language Tree Structures for Visual Grounding

Grounding natural language in images, such as localizing "the black dog on the left of the tree", is one of the core problems in artificial intelligence, as it needs to comprehend the fine-grained and compositional language space. However, existing solutions rely on the association between the holistic language features and visual features, while neglect the nature of compositional reasoning implied in the language. In this paper, we propose a natural language grounding model that can automatically compose a binary tree structure for parsing the language and then perform visual reasoning along the tree in a bottom-up fashion. We call our model RVG-TREE: Recursive Grounding Tree, which is inspired by the intuition that any language expression can be recursively decomposed into two constituent parts, and the grounding confidence score can be recursively accumulated by calculating their grounding scores returned by sub-trees. RVG-TREE can be trained end-to-end by using the Straight-Through Gumbel-Softmax estimator that allows the gradients from the continuous score functions passing through the discrete tree construction. Experiments on several benchmarks show that our model achieves the state-of-the-art performance with more explainable reasoning.

arXiv:1904.10947

On the Contributions of Visual and Textual Supervision in Low-Resource Semantic Speech Retrieval

Recent work has shown that speech paired with images can be used to learn semantically meaningful speech representations even without any textual supervision. In real-world low-resource settings, however, we often have access to some transcribed speech. We study whether and how visual grounding is useful in the presence of varying amounts of textual supervision. In particular, we consider the task of semantic speech retrieval in a low-resource setting. We use a previously studied data set and task, where models are trained on images with spoken captions and evaluated on human judgments of semantic relevance. We propose a multitask learning approach to leverage both visual and textual modalities, with visual supervision in the form of keyword probabilities from an external tagger. We find that visual grounding is helpful even in the presence of textual supervision, and we analyze this effect over a range of sizes of transcribed data sets. With ~5 hours of transcribed speech, we obtain 23% higher average precision when also using visual supervision.

arXiv:1904.07078

Semantic query-by-example speech search using visual grounding

A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode retrieval. Here we consider how such models can be used for query-by-example (QbE) search, the task of retrieving utterances relevant to a given spoken query. We are particularly interested in semantic QbE, where the task is not only to retrieve utterances containing exact instances of the query, but also utterances whose meaning is relevant to the query. We follow a segmental QbE approach where variable-duration speech segments (queries, search utterances) are mapped to fixed-dimensional embedding vectors. We show that a QbE system using an embedding function trained on visually grounded speech data outperforms a purely acoustic QbE system in terms of both exact and semantic retrieval performance.

arXiv:1904.03589공식 코드 · Papers with Code

Modularized Textual Grounding for Counterfactual Resilience

Computer Vision applications often require a textual grounding module with precision, interpretability, and resilience to counterfactual inputs/queries. To achieve high grounding precision, current textual grounding methods heavily rely on large-scale training data with manual annotations at the pixel level. Such annotations are expensive to obtain and thus severely narrow the model's scope of real-world applications. Moreover, most of these methods sacrifice interpretability, generalizability, and they neglect the importance of being resilient to counterfactual inputs. To address these issues, we propose a visual grounding system which is 1) end-to-end trainable in a weakly supervised fashion with only image-level annotations, and 2) counterfactually resilient owing to the modular design. Specifically, we decompose textual descriptions into three levels: entity, semantic attribute, color information, and perform compositional grounding progressively. We validate our model through a series of experiments and demonstrate its improvement over the state-of-the-art methods. In particular, our model's performance not only surpasses other weakly/un-supervised methods and even approaches the strongly supervised ones, but also is interpretable for decision making and performs much better in face of counterfactual classes than all the others.

arXiv:1904.02794

VQD: Visual Query Detection in Natural Scenes

We propose Visual Query Detection (VQD), a new visual grounding task. In VQD, a system is guided by natural language to localize a variable number of objects in an image. VQD is related to visual referring expression recognition, where the task is to localize only one object. We describe the first dataset for VQD and we propose baseline algorithms that demonstrate the difficulty of the task compared to referring expression recognition.

arXiv:1904.02225

Revisiting Visual Grounding

We revisit a particular visual grounding method: the "Image Retrieval Using Scene Graphs" (IRSG) system of Johnson et al. (2015). Our experiments indicate that the system does not effectively use its learned object-relationship models. We also look closely at the IRSG dataset, as well as the widely used Visual Relationship Dataset (VRD) that is adapted from it. We find that these datasets exhibit biases that allow methods that ignore relationships to perform relatively well. We also describe several other problems with the IRSG dataset, and report on experiments using a subset of the dataset in which the biases and other problems are removed. Our studies contribute to a more general effort: that of better understanding what machine learning methods that combine language and vision actually learn and what popular datasets actually test.

arXiv:1903.11649

Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment

We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a `downstream' task to guide the process of phrase localization. Our method, as a first step, infers the latent correspondences between regions-of-interest (RoIs) and phrases in the caption and creates a discriminative image representation using these matched RoIs. In a subsequent step, this (learned) representation is aligned with the caption. Our key contribution lies in building this `caption-conditioned' image encoding which tightly couples both the tasks and allows the weak supervision to effectively guide visual grounding. We provide an extensive empirical and qualitative analysis to investigate the different components of our proposed model and compare it with competitive baselines. For phrase localization, we report an improvement of 4.9% (absolute) over the prior state-of-the-art on the VisualGenome dataset. We also report results that are at par with the state-of-the-art on the downstream caption-to-image retrieval task on COCO and Flickr30k datasets.

arXiv:1903.11393공식 코드 · Papers with Code

Learning semantic sentence representations from visually grounded language without lexical knowledge

Current approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word embeddings. We use a multimodal sentence encoder trained on a corpus of images with matching text captions to produce visually grounded sentence embeddings. Deep Neural Networks are trained to map the two modalities to a common embedding space such that for an image the corresponding caption can be retrieved and vice versa. We show that our model achieves results comparable to the current state-of-the-art on two popular image-caption retrieval benchmark data sets: MSCOCO and Flickr8k. We evaluate the semantic content of the resulting sentence embeddings using the data from the Semantic Textual Similarity benchmark task and show that the multimodal embeddings correlate well with human semantic similarity judgements. The system achieves state-of-the-art results on several of these benchmarks, which shows that a system trained solely on multimodal data, without assuming any word representations, is able to capture sentence level semantics. Importantly, this result shows that we do not need prior knowledge of lexical level semantics in order to model sentence level semantics. These findings demonstrate the importance of visual information in semantics.

arXiv:1902.09368공식 코드 · Papers with Code

Dual Attention Networks for Visual Reference Resolution in Visual Dialog

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.

arXiv:1902.04213

You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding

Visual Grounding (VG) aims to locate the most relevant region in an image, based on a flexible natural language query but not a pre-defined label, thus it can be a more useful technique than object detection in practice. Most state-of-the-art methods in VG operate in a two-stage manner, wherein the first stage an object detector is adopted to generate a set of object proposals from the input image and the second stage is simply formulated as a cross-modal matching problem that finds the best match between the language query and all region proposals. This is rather inefficient because there might be hundreds of proposals produced in the first stage that need to be compared in the second stage, not to mention this strategy performs inaccurately. In this paper, we propose an simple, intuitive and much more elegant one-stage detection based method that joints the region proposal and matching stage as a single detection network. The detection is conditioned on the input query with a stack of novel Relation-to-Attention modules that transform the image-to-query relationship to an relation map, which is used to predict the bounding box directly without proposing large numbers of useless region proposals. During the inference, our approach is about 20x ~ 30x faster than previous methods and, remarkably, it achieves 18% ~ 41% absolute performance improvement on top of the state-of-the-art results on several benchmark datasets. We release our code and all the pre-trained models at https://github.com/openblack/rvg.

arXiv:1902.03751

Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded

Many vision and language models suffer from poor visual grounding - often falling back on easy-to-learn language priors rather than basing their decisions on visual concepts in the image. In this work, we propose a generic approach called Human Importance-aware Network Tuning (HINT) that effectively leverages human demonstrations to improve visual grounding. HINT encourages deep networks to be sensitive to the same input regions as humans. Our approach optimizes the alignment between human attention maps and gradient-based network importances - ensuring that models learn not just to look at but rather rely on visual concepts that humans found relevant for a task when making predictions. We apply HINT to Visual Question Answering and Image Captioning tasks, outperforming top approaches on splits that penalize over-reliance on language priors (VQA-CP and robust captioning) using human attention demonstrations for just 6% of the training data.

arXiv:1812.03299

Learning to Assemble Neural Module Tree Networks for Visual Grounding

Visual grounding, a task to ground (i.e., localize) natural language in images, essentially requires composite visual reasoning. However, existing methods over-simplify the composite nature of language into a monolithic sentence embedding or a coarse composition of subject-predicate-object triplet. In this paper, we propose to ground natural language in an intuitive, explainable, and composite fashion as it should be. In particular, we develop a novel modular network called Neural Module Tree network (NMTree) that regularizes the visual grounding along the dependency parsing tree of the sentence, where each node is a neural module that calculates visual attention according to its linguistic feature, and the grounding score is accumulated in a bottom-up direction where as needed. NMTree disentangles the visual grounding from the composite reasoning, allowing the former to only focus on primitive and easy-to-generalize patterns. To reduce the impact of parsing errors, we train the modules and their assembly end-to-end by using the Gumbel-Softmax approximation and its straight-through gradient estimator, accounting for the discrete nature of module assembly. Overall, the proposed NMTree consistently outperforms the state-of-the-arts on several benchmarks. Qualitative results show explainable grounding score calculation in great detail.

arXiv:1812.00500

Multi-task Learning of Hierarchical Vision-Language Representation

It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and trained them on its dedicated datasets. Although this approach has seen a certain degree of success, it comes with difficulties of understanding relations among different tasks and transferring the knowledge learned for a task to others. We propose a multi-task learning approach that enables to learn vision-language representation that is shared by many tasks from their diverse datasets. The representation is hierarchical, and prediction for each task is computed from the representation at its corresponding level of the hierarchy. We show through experiments that our method consistently outperforms previous single-task-learning methods on image caption retrieval, visual question answering, and visual grounding. We also analyze the learned hierarchical representation by visualizing attention maps generated in our network.