Recent neural models have shown significant progress on the problem of generating short descriptive texts conditioned on a small number of database records. In this work, we suggest a slightly more difficult data-to-text generation task, and investigate how effective current approaches are on this task. In particular, we introduce a new, large-scale corpus of data records paired with descriptive documents, propose a series of extractive evaluation methods for analyzing performance, and obtain baseline results using current neural generation methods. Experiments show that these models produce fluent text, but fail to convincingly approximate human-generated documents. Moreover, even templated baselines exceed the performance of these neural models on some metrics, though copy- and reconstruction-based extensions lead to noticeable improvements.
Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images, labeling each with a short descriptive phrase. We identify two key challenges of dense captioning that need to be properly addressed when tackling the problem. First, dense visual concept annotations in each image are associated with highly overlapping target regions, making accurate localization of each visual concept challenging. Second, the large amount of visual concepts makes it hard to recognize each of them by appearance alone. We propose a new model pipeline based on two novel ideas, joint inference and context fusion, to alleviate these two challenges. We design our model architecture in a methodical manner and thoroughly evaluate the variations in architecture. Our final model, compact and efficient, achieves state-of-the-art accuracy on Visual Genome for dense captioning with a relative gain of 73\% compared to the previous best algorithm. Qualitative experiments also reveal the semantic capabilities of our model in dense captioning.
Despite the ubiquity of transportation data, methods to infer the state parameters of a network either ignore sensitivity of route decisions, require route enumeration for parameterizing descriptive models of route selection, or require complex bilevel models of route assignment behavior. These limitations prevent modelers from fully exploiting ubiquitous data in monitoring transportation networks. Inverse optimization methods that capture network route choice behavior can address this gap, but they are designed to take observations of the same model to learn the parameters of that model, which is statistically inefficient (e.g. requires estimating population route and link flows). New inverse optimization models and supporting algorithms are proposed to learn the parameters of heterogeneous travelers' route behavior to infer shared network state parameters (e.g. link capacity dual prices). The inferred values are consistent with observations of each agent's optimization behavior. We prove that the method can obtain unique dual prices for a network shared by these agents in polynomial time. Four experiments are conducted. The first one, conducted on a 4-node network, verifies the methodology to obtain heterogeneous link cost parameters even when multinomial or mixed logit models would not be meaningfully estimated. The second is a parameter recovery test on the Nguyen-Dupuis network that shows that unique latent link capacity dual prices can be inferred using the proposed method. The third test on the same network demonstrates how a monitoring system in an online learning environment can be designed using this method. The last test demonstrates this learning on real data obtained from a freeway network in Queens, New York, using only real-time Google Maps queries.
We propose a deep learning-based solution for the problem of feature learning in one-class classification. The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive features while maintaining a low intra-class variance in the feature space for the given class. For this purpose two loss functions, compactness loss and descriptiveness loss are proposed along with a parallel CNN architecture. A template matching-based framework is introduced to facilitate the testing process. Extensive experiments on publicly available anomaly detection, novelty detection and mobile active authentication datasets show that the proposed Deep One-Class (DOC) classification method achieves significant improvements over the state-of-the-art.
In the last three decades, human visual attention has been a topic of great interest in various disciplines. In computer vision, many models have been proposed to predict the distribution of human fixations on a visual stimulus. Recently, thanks to the creation of large collections of data, machine learning algorithms have obtained state-of-the-art performance on the task of saliency map estimation. On the other hand, computational models of scanpath are much less studied. Works are often only descriptive or task specific. This is due to the fact that the scanpath is harder to model because it must include the description of a dynamic. General purpose computational models are present in the literature, but are then evaluated in tasks of saliency prediction, losing therefore information about the dynamics and the behaviour. In addition, two technical reasons have limited the research. The first reason is the lack of robust and uniformly used set of metrics to compare the similarity between scanpath. The second reason is the lack of sufficiently large and varied scanpath datasets. In this report we want to help in both directions. We present FixaTons, a large collection of datasets human scanpaths (temporally ordered sequences of fixations) and saliency maps. It comes along with a software library for easy data usage, statistics calculation and implementation of metrics for scanpath and saliency prediction evaluation.
Combining Generative Adversarial Networks (GANs) with encoders that learn to encode data points has shown promising results in learning data representations in an unsupervised way. We propose a framework that combines an encoder and a generator to learn disentangled representations which encode meaningful information about the data distribution without the need for any labels. While current approaches focus mostly on the generative aspects of GANs, our framework can be used to perform inference on both real and generated data points. Experiments on several data sets show that the encoder learns interpretable, disentangled representations which encode descriptive properties and can be used to sample images that exhibit specific characteristics.
Despite the availability of a huge amount of video data accompanied by descriptive texts, it is not always easy to exploit the information contained in natural language in order to automatically recognize video concepts. Towards this goal, in this paper we use textual cues as means of supervision, introducing two weakly supervised techniques that extend the Multiple Instance Learning (MIL) framework: the Fuzzy Sets Multiple Instance Learning (FSMIL) and the Probabilistic Labels Multiple Instance Learning (PLMIL). The former encodes the spatio-temporal imprecision of the linguistic descriptions with Fuzzy Sets, while the latter models different interpretations of each description's semantics with Probabilistic Labels, both formulated through a convex optimization algorithm. In addition, we provide a novel technique to extract weak labels in the presence of complex semantics, that consists of semantic similarity computations. We evaluate our methods on two distinct problems, namely face and action recognition, in the challenging and realistic setting of movies accompanied by their screenplays, contained in the COGNIMUSE database. We show that, on both tasks, our method considerably outperforms a state-of-the-art weakly supervised approach, as well as other baselines.
Traditional approaches to stereo visual SLAM rely on point features to estimate the camera trajectory and build a map of the environment. In low-textured environments, though, it is often difficult to find a sufficient number of reliable point features and, as a consequence, the performance of such algorithms degrades. This paper proposes PL-SLAM, a stereo visual SLAM system that combines both points and line segments to work robustly in a wider variety of scenarios, particularly in those where point features are scarce or not well-distributed in the image. PL-SLAM leverages both points and segments at all the instances of the process: visual odometry, keyframe selection, bundle adjustment, etc. We contribute also with a loop closure procedure through a novel bag-of-words approach that exploits the combined descriptive power of the two kinds of features. Additionally, the resulting map is richer and more diverse in 3D elements, which can be exploited to infer valuable, high-level scene structures like planes, empty spaces, ground plane, etc. (not addressed in this work). Our proposal has been tested with several popular datasets (such as KITTI and EuRoC), and is compared to state of the art methods like ORB-SLAM, revealing a more robust performance in most of the experiments, while still running in real-time. An open source version of the PL-SLAM C++ code will be released for the benefit of the community.
Automatic colorization is the process of adding color to greyscale images. We condition this process on language, allowing end users to manipulate a colorized image by feeding in different captions. We present two different architectures for language-conditioned colorization, both of which produce more accurate and plausible colorizations than a language-agnostic version. Through this language-based framework, we can dramatically alter colorizations by manipulating descriptive color words in captions.
Anomaly detection has numerous applications and has been studied vastly. We consider a complementary problem that has a much sparser literature: anomaly description. Interpretation of anomalies is crucial for practitioners for sense-making, troubleshooting, and planning actions. To this end, we present a new approach called x-PACS (for eXplaining Patterns of Anomalies with Characterizing Subspaces), which "reverse-engineers" the known anomalies by identifying (1) the groups (or patterns) that they form, and (2) the characterizing subspace and feature rules that separate each anomalous pattern from normal instances. Explaining anomalies in groups not only saves analyst time and gives insight into various types of anomalies, but also draws attention to potentially critical, repeating anomalies. In developing x-PACS, we first construct a desiderata for the anomaly description problem. From a descriptive data mining perspective, our method exhibits five desired properties in our desiderata. Namely, it can unearth anomalous patterns (i) of multiple different types, (ii) hidden in arbitrary subspaces of a high dimensional space, (iii) interpretable by the analysts, (iv) different from normal patterns of the data, and finally (v) succinct, providing the shortest data description. Furthermore, x-PACS is highly parallelizable and scales linearly in terms of data size. No existing work on anomaly description satisfies all of these properties simultaneously. While not our primary goal, the anomalous patterns we find serve as interpretable "signatures" and can be used for detection. We show the effectiveness of x-PACS in explanation as well as detection on real-world datasets as compared to state-of-the-art.
We address the task of detecting foiled image captions, i.e. identifying whether a caption contains a word that has been deliberately replaced by a semantically similar word, thus rendering it inaccurate with respect to the image being described. Solving this problem should in principle require a fine-grained understanding of images to detect linguistically valid perturbations in captions. In such contexts, encoding sufficiently descriptive image information becomes a key challenge. In this paper, we demonstrate that it is possible to solve this task using simple, interpretable yet powerful representations based on explicit object information. Our models achieve state-of-the-art performance on a standard dataset, with scores exceeding those achieved by humans on the task. We also measure the upper-bound performance of our models using gold standard annotations. Our analysis reveals that the simpler model performs well even without image information, suggesting that the dataset contains strong linguistic bias.
Linguistic style is an essential part of written communication, with the power to affect both clarity and attractiveness. With recent advances in vision and language, we can start to tackle the problem of generating image captions that are both visually grounded and appropriately styled. Existing approaches either require styled training captions aligned to images or generate captions with low relevance. We develop a model that learns to generate visually relevant styled captions from a large corpus of styled text without aligned images. The core idea of this model, called SemStyle, is to separate semantics and style. One key component is a novel and concise semantic term representation generated using natural language processing techniques and frame semantics. In addition, we develop a unified language model that decodes sentences with diverse word choices and syntax for different styles. Evaluations, both automatic and manual, show captions from SemStyle preserve image semantics, are descriptive, and are style shifted. More broadly, this work provides possibilities to learn richer image descriptions from the plethora of linguistic data available on the web.
We propose DuoRC, a novel dataset for Reading Comprehension (RC) that motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets. DuoRC contains 186,089 unique question-answer pairs created from a collection of 7680 pairs of movie plots where each pair in the collection reflects two versions of the same movie - one from Wikipedia and the other from IMDb - written by two different authors. We asked crowdsourced workers to create questions from one version of the plot and a different set of workers to extract or synthesize answers from the other version. This unique characteristic of DuoRC where questions and answers are created from different versions of a document narrating the same underlying story, ensures by design, that there is very little lexical overlap between the questions created from one version and the segments containing the answer in the other version. Further, since the two versions have different levels of plot detail, narration style, vocabulary, etc., answering questions from the second version requires deeper language understanding and incorporating external background knowledge. Additionally, the narrative style of passages arising from movie plots (as opposed to typical descriptive passages in existing datasets) exhibits the need to perform complex reasoning over events across multiple sentences. Indeed, we observe that state-of-the-art neural RC models which have achieved near human performance on the SQuAD dataset, even when coupled with traditional NLP techniques to address the challenges presented in DuoRC exhibit very poor performance (F1 score of 37.42% on DuoRC v/s 86% on SQuAD dataset). This opens up several interesting research avenues wherein DuoRC could complement other RC datasets to explore novel neural approaches for studying language understanding.
The General Video Game AI competitions have been the testing ground for several techniques for game playing, such as evolutionary computation techniques, tree search algorithms, hyper heuristic based or knowledge based algorithms. So far the metrics used to evaluate the performance of agents have been win ratio, game score and length of games. In this paper we provide a wider set of metrics and a comparison method for evaluating and comparing agents. The metrics and the comparison method give shallow introspection into the agent's decision making process and they can be applied to any agent regardless of its algorithmic nature. In this work, the metrics and the comparison method are used to measure the impact of the terms that compose a tree policy of an MCTS based agent, comparing with several baseline agents. The results clearly show how promising such general approach is and how it can be useful to understand the behaviour of an AI agent, in particular, how the comparison with baseline agents can help understanding the shape of the agent decision landscape. The presented metrics and comparison method represent a step toward to more descriptive ways of logging and analysing agent's behaviours.
In this paper, we introduce a conceptually simple network for generating discriminative tissue-level segmentation masks for the purpose of breast cancer diagnosis. Our method efficiently segments different types of tissues in breast biopsy images while simultaneously predicting a discriminative map for identifying important areas in an image. Our network, Y-Net, extends and generalizes U-Net by adding a parallel branch for discriminative map generation and by supporting convolutional block modularity, which allows the user to adjust network efficiency without altering the network topology. Y-Net delivers state-of-the-art segmentation accuracy while learning 6.6x fewer parameters than its closest competitors. The addition of descriptive power from Y-Net's discriminative segmentation masks improve diagnostic classification accuracy by 7% over state-of-the-art methods for diagnostic classification. Source code is available at: https://sacmehta.github.io/YNet.
One property that remains lacking in image captions generated by contemporary methods is discriminability: being able to tell two images apart given the caption for one of them. We propose a way to improve this aspect of caption generation. By incorporating into the captioning training objective a loss component directly related to ability (by a machine) to disambiguate image/caption matches, we obtain systems that produce much more discriminative caption, according to human evaluation. Remarkably, our approach leads to improvement in other aspects of generated captions, reflected by a battery of standard scores such as BLEU, SPICE etc. Our approach is modular and can be applied to a variety of model/loss combinations commonly proposed for image captioning.
We present an image-based VIirtual Try-On Network (VITON) without using 3D information in any form, which seamlessly transfers a desired clothing item onto the corresponding region of a person using a coarse-to-fine strategy. Conditioned upon a new clothing-agnostic yet descriptive person representation, our framework first generates a coarse synthesized image with the target clothing item overlaid on that same person in the same pose. We further enhance the initial blurry clothing area with a refinement network. The network is trained to learn how much detail to utilize from the target clothing item, and where to apply to the person in order to synthesize a photo-realistic image in which the target item deforms naturally with clear visual patterns. Experiments on our newly collected Zalando dataset demonstrate its promise in the image-based virtual try-on task over state-of-the-art generative models.
질(qualities)과 양(quantities)을 자연스럽게 다루는 데 도움이 되고 정확성 검증 작업을 크게 단순화하는 언어인 Soda(Symbolic Objective Descriptive Analysis)를 제안한다. 컴퓨터 시스템에 대한 복잡한 요구사항을 인코딩하기 위한 서술적 언어 설계에서 영감을 받은 본 언어의 핵심 속성을 제시하고, 이러한 핵심 속성이 간단한 정의로 해당 요구사항을 모델링하기 위해 어떻게 다루어져야 하는지 설명한다. 문제를 쉽게 기술하는 데 도움이 되는 도구의 개요를 제공하며, 이는 더 투명하고 오류 가능성이 낮다고 본다.
RS-Agent는 구조화된 작업 계획과 도구 오케스트레이션을 통해 사용자 의도를 전문적인 원격 탐사 워크플로우와 연결하는 도메인 적응형 지능 에이전트로, 중앙 컨트롤러, 동적 툴킷, Solution Space, Knowledge Space의 네 가지 구성요소로 이루어진다. Task-Aware Retrieval과 가중 이중 경로 검색-증강 생성 방법인 DualRAG를 도입하여 9개 데이터셋, 18개 원격 탐사 작업 실험에서 95% 이상의 작업 계획 정확도와 함께 장면 분류, 객체 계수, 시각적 질의응답에서 최신 MLLM 대비 현저히 높은 성능을 달성하였다.