Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN). In this paper, we present VISITRON, a multi-modal Transformer-based navigator better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN). VISITRON is trained to: i) identify and associate object-level concepts and semantics between the environment and dialogue history, ii) identify when to interact vs. navigate via imitation learning of a binary classification head. We perform extensive pre-training and fine-tuning ablations with VISITRON to gain empirical insights and improve performance on CVDN. VISITRON's ability to identify when to interact leads to a natural generalization of the game-play mode introduced by Roman et al. (arXiv:2005.00728) for enabling the use of such models in different environments. VISITRON is competitive with models on the static CVDN leaderboard and attains state-of-the-art performance on the Success weighted by Path Length (SPL) metric.
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, an end-to-end video object detection model based on a spatial-temporal Transformer architecture. The goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow, recurrent neural networks, relation networks. Besides, benefited from the object query design in DETR, our method does not need complicated post-processing methods such as Seq-NMS or Tubelet rescoring, which keeps the pipeline simple and clean. In particular, we present temporal Transformer to aggregate both the spatial object queries and the feature memories of each frame. Our temporal Transformer consists of three components: Temporal Deformable Transformer Encoder (TDTE) to encode the multiple frame spatial details, Temporal Query Encoder (TQE) to fuse object queries, and Temporal Deformable Transformer Decoder to obtain current frame detection results. These designs boost the strong baseline deformable DETR by a significant margin (3%-4% mAP) on the ImageNet VID dataset. TransVOD yields comparable results performance on the benchmark of ImageNet VID. We hope our TransVOD can provide a new perspective for video object detection. Code will be made publicly available at https://github.com/SJTU-LuHe/TransVOD.
One of the most fundamental and information-laden actions humans do is to look at objects. However, a survey of current works reveals that existing gaze-related datasets annotate only the pixel being looked at, and not the boundaries of a specific object of interest. This lack of object annotation presents an opportunity for further advancing gaze estimation research. To this end, we present a challenging new task called gaze object prediction, where the goal is to predict a bounding box for a person's gazed-at object. To train and evaluate gaze networks on this task, we present the Gaze On Objects (GOO) dataset. GOO is composed of a large set of synthetic images (GOO Synth) supplemented by a smaller subset of real images (GOO-Real) of people looking at objects in a retail environment. Our work establishes extensive baselines on GOO by re-implementing and evaluating selected state-of-the art models on the task of gaze following and domain adaptation. Code is available on github.
3D visual grounding aims at grounding a natural language description about a 3D scene, usually represented in the form of 3D point clouds, to the targeted object region. Point clouds are sparse, noisy, and contain limited semantic information compared with 2D images. These inherent limitations make the 3D visual grounding problem more challenging. In this study, we propose 2D Semantics Assisted Training (SAT) that utilizes 2D image semantics in the training stage to ease point-cloud-language joint representation learning and assist 3D visual grounding. The main idea is to learn auxiliary alignments between rich, clean 2D object representations and the corresponding objects or mentioned entities in 3D scenes. SAT takes 2D object semantics, i.e., object label, image feature, and 2D geometric feature, as the extra input in training but does not require such inputs during inference. By effectively utilizing 2D semantics in training, our approach boosts the accuracy on the Nr3D dataset from 37.7% to 49.2%, which significantly surpasses the non-SAT baseline with the identical network architecture and inference input. Our approach outperforms the state of the art by large margins on multiple 3D visual grounding datasets, i.e., +10.4% absolute accuracy on Nr3D, +9.9% on Sr3D, and +5.6% on ScanRef.
This paper proposes a novel deep learning-based video object matting method that can achieve temporally coherent matting results. Its key component is an attention-based temporal aggregation module that maximizes image matting networks' strength for video matting networks. This module computes temporal correlations for pixels adjacent to each other along the time axis in feature space, which is robust against motion noises. We also design a novel loss term to train the attention weights, which drastically boosts the video matting performance. Besides, we show how to effectively solve the trimap generation problem by fine-tuning a state-of-the-art video object segmentation network with a sparse set of user-annotated keyframes. To facilitate video matting and trimap generation networks' training, we construct a large-scale video matting dataset with 80 training and 28 validation foreground video clips with ground-truth alpha mattes. Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion. Our code and dataset can be found at: https://github.com/yunkezhang/TCVOM
In contrast to the generic object, aerial targets are often non-axis aligned with arbitrary orientations having the cluttered surroundings. Unlike the mainstreamed approaches regressing the bounding box orientations, this paper proposes an effective adaptive points learning approach to aerial object detection by taking advantage of the adaptive points representation, which is able to capture the geometric information of the arbitrary-oriented instances. To this end, three oriented conversion functions are presented to facilitate the classification and localization with accurate orientation. Moreover, we propose an effective quality assessment and sample assignment scheme for adaptive points learning toward choosing the representative oriented reppoints samples during training, which is able to capture the non-axis aligned features from adjacent objects or background noises. A spatial constraint is introduced to penalize the outlier points for roust adaptive learning. Experimental results on four challenging aerial datasets including DOTA, HRSC2016, UCAS-AOD and DIOR-R, demonstrate the efficacy of our proposed approach. The source code is availabel at: https://github.com/LiWentomng/OrientedRepPoints.
This paper tackles the 3D object detection problem, which is of vital importance for applications such as autonomous driving. Our framework uses a Machine Learning (ML) pipeline on a combination of monocular camera and LiDAR data to detect vehicles in the surrounding 3D space of a moving platform. It uses frustum region proposals generated by State-Of-The-Art (SOTA) 2D object detectors to segment LiDAR point clouds into point clusters which represent potentially individual objects. We evaluate the performance of classical ML algorithms as part of an holistic pipeline for estimating the parameters of 3D bounding boxes which surround the vehicles around the moving platform. Our results demonstrate an efficient and accurate inference on a validation set, achieving an overall accuracy of 87.1%.
Physical processes, camera movement, and unpredictable environmental conditions like the presence of dust can induce noise and artifacts in video feeds. We observe that popular unsupervised MOT methods are dependent on noise-free inputs. We show that the addition of a small amount of artificial random noise causes a sharp degradation in model performance on benchmark metrics. We resolve this problem by introducing a robust unsupervised multi-object tracking (MOT) model: AttU-Net. The proposed single-head attention model helps limit the negative impact of noise by learning visual representations at different segment scales. AttU-Net shows better unsupervised MOT tracking performance over variational inference-based state-of-the-art baselines. We evaluate our method in the MNIST-MOT and the Atari game video benchmark. We also provide two extended video datasets: ``Kuzushiji-MNIST MOT'' which consists of moving Japanese characters and ``Fashion-MNIST MOT'' to validate the effectiveness of the MOT models.
Recently few-shot object detection is widely adopted to deal with data-limited situations. While most previous works merely focus on the performance on few-shot categories, we claim that detecting all classes is crucial as test samples may contain any instances in realistic applications, which requires the few-shot detector to learn new concepts without forgetting. Through analysis on transfer learning based methods, some neglected but beneficial properties are utilized to design a simple yet effective few-shot detector, Retentive R-CNN. It consists of Bias-Balanced RPN to debias the pretrained RPN and Re-detector to find few-shot class objects without forgetting previous knowledge. Extensive experiments on few-shot detection benchmarks show that Retentive R-CNN significantly outperforms state-of-the-art methods on overall performance among all settings as it can achieve competitive results on few-shot classes and does not degrade the base class performance at all. Our approach has demonstrated that the long desired never-forgetting learner is available in object detection.
In recent years, developing AI for robotics has raised much attention. The interaction of vision and language of robots is particularly difficult. We consider that giving robots an understanding of visual semantics and language semantics will improve inference ability. In this paper, we propose a novel method-VSGM (Visual Semantic Graph Memory), which uses the semantic graph to obtain better visual image features, improve the robot's visual understanding ability. By providing prior knowledge of the robot and detecting the objects in the image, it predicts the correlation between the attributes of the object and the objects and converts them into a graph-based representation; and mapping the object in the image to be a top-down egocentric map. Finally, the important object features of the current task are extracted by Graph Neural Networks. The method proposed in this paper is verified in the ALFRED (Action Learning From Realistic Environments and Directives) dataset. In this dataset, the robot needs to perform daily indoor household tasks following the required language instructions. After the model is added to the VSGM, the task success rate can be improved by 6~10%.
Recently, general salient object detection (SOD) has made great progress with the rapid development of deep neural networks. However, task-aware SOD has hardly been studied due to the lack of task-specific datasets. In this paper, we construct a driving task-oriented dataset where pixel-level masks of salient objects have been annotated. Comparing with general SOD datasets, we find that the cross-domain knowledge difference and task-specific scene gap are two main challenges to focus the salient objects when driving. Inspired by these findings, we proposed a baseline model for the driving task-aware SOD via a knowledge transfer convolutional neural network. In this network, we construct an attentionbased knowledge transfer module to make up the knowledge difference. In addition, an efficient boundary-aware feature decoding module is introduced to perform fine feature decoding for objects in the complex task-specific scenes. The whole network integrates the knowledge transfer and feature decoding modules in a progressive manner. Experiments show that the proposed dataset is very challenging, and the proposed method outperforms 12 state-of-the-art methods on the dataset, which facilitates the development of task-aware SOD.
The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction. Virtually all of the previous attempts to map multiple dynamic objects have evolved to store individual objects in separate reconstruction volumes and track the relative pose between them. While simple and intuitive, such formulation does not scale well with respect to the number of objects in the scene and introduces the need for an explicit occlusion handling strategy. In contrast, we propose a map representation that allows maintaining a single volume for the entire scene and all the objects therein. To this end, we introduce a novel multi-object TSDF formulation that can encode multiple object surfaces at any given location in the map. In a multiple dynamic object tracking and reconstruction scenario, our representation allows maintaining accurate reconstruction of surfaces even while they become temporarily occluded by other objects moving in their proximity. We evaluate the proposed TSDF++ formulation on a public synthetic dataset and demonstrate its ability to preserve reconstructions of occluded surfaces when compared to the standard TSDF map representation.
The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network. However, this joint detection and tracking method still suffers from high identity switches due to the inferior association method. To reduce the high number of identity switches and improve the tracking accuracy, in this paper, we propose to incorporate a simple tracked object bounding box and overlapping prediction based on the current frame onto the CenterTrack algorithm. Specifically, we propose an Intersection over Union (IOU) distance cost matrix in the association step instead of simple point displacement distance. We evaluate our proposed tracker on the MOT17 test dataset, showing that our proposed method can reduce identity switches significantly by 22.6% and obtain a notable improvement of 1.5% in IDF1 compared to the original CenterTrack's under the same tracklet lifetime. The source code is released at https://github.com/Nanyangny/CenterTrack-IOU.
Idier et al. [IEEE Trans. Comput. Imaging 4(1), 2018] propose a method which achieves superresolution in the microscopy setting by leveraging random speckle illumination and knowledge about statistical second order moments for the illumination patterns and model noise. This is achieved without any assumptions on the sparsity of the imaged object. In this paper, we show that their technique can be extended to photoacoustic tomography. We propose a simple algorithm for doing the reconstruction which only requires a small number of linear algebra steps. It is therefore much faster than the iterative method used by Idier et al. We also propose a new representation of the imaged object based on Dirac delta expansion functions.
In this work, we address multi-modal information needs that contain text questions and images by focusing on passage retrieval for outside-knowledge visual question answering. This task requires access to outside knowledge, which in our case we define to be a large unstructured passage collection. We first conduct sparse retrieval with BM25 and study expanding the question with object names and image captions. We verify that visual clues play an important role and captions tend to be more informative than object names in sparse retrieval. We then construct a dual-encoder dense retriever, with the query encoder being LXMERT, a multi-modal pre-trained transformer. We further show that dense retrieval significantly outperforms sparse retrieval that uses object expansion. Moreover, dense retrieval matches the performance of sparse retrieval that leverages human-generated captions.
Concealed object detection in Terahertz imaging is an urgent need for public security and counter-terrorism. In this paper, we provide a public dataset for evaluating multi-object detection algorithms in active Terahertz imaging resolution 5 mm by 5 mm. To the best of our knowledge, this is the first public Terahertz imaging dataset prepared to evaluate object detection algorithms. Object detection on this dataset is much more difficult than on those standard public object detection datasets due to its inferior imaging quality. Facing the problem of imbalanced samples in object detection and hard training samples, we evaluate four popular detectors: YOLOv3, YOLOv4, FRCN-OHEM, and RetinaNet on this dataset. Experimental results indicate that the RetinaNet achieves the highest mAP. In addition, we demonstrate that hiding objects in different parts of the human body affect detection accuracy. The dataset is available at https://github.com/LingLIx/THz_Dataset.
This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets, which unrealistically assume that each image should contain at least one clear and uncluttered salient object. This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets. However, these models are still far from satisfactory when applied to real-world scenes. Based on our analyses, we propose a new high-quality dataset and update the previous saliency benchmark. Specifically, our dataset, called Salient Objects in Clutter~\textbf{(SOC)}, includes images with both salient and non-salient objects from several common object categories. In addition to object category annotations, each salient image is accompanied by attributes that reflect common challenges in common scenes, which can help provide deeper insight into the SOD problem. Further, with a given saliency encoder, e.g., the backbone network, existing saliency models are designed to achieve mapping from the training image set to the training ground-truth set. We, therefore, argue that improving the dataset can yield higher performance gains than focusing only on the decoder design. With this in mind, we investigate several dataset-enhancement strategies, including label smoothing to implicitly emphasize salient boundaries, random image augmentation to adapt saliency models to various scenarios, and self-supervised learning as a regularization strategy to learn from small datasets. Our extensive results demonstrate the effectiveness of these tricks. We also provide a comprehensive benchmark for SOD, which can be found in our repository: https://github.com/DengPingFan/SODBenchmark.
Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature. While template-based approaches, such as parametric shape models, have achieved great success in modeling the "closed world" of known object categories, they cannot well handle the "open-world" of novel object categories or outlier shapes. In this work, we introduce a template-free approach to learn 3D shapes from a single video. It adopts an analysis-by-synthesis strategy that forward-renders object silhouette, optical flow, and pixel values to compare with video observations, which generates gradients to adjust the camera, shape and motion parameters. Without using a category-specific shape template, our method faithfully reconstructs nonrigid 3D structures from videos of human, animals, and objects of unknown classes. Code will be available at lasr-google.github.io .
In order to interact with the world, agents must be able to predict the results of the world's dynamics. A natural approach to learn about these dynamics is through video prediction, as cameras are ubiquitous and powerful sensors. Direct pixel-to-pixel video prediction is difficult, does not take advantage of known priors, and does not provide an easy interface to utilize the learned dynamics. Object-centric video prediction offers a solution to these problems by taking advantage of the simple prior that the world is made of objects and by providing a more natural interface for control. However, existing object-centric video prediction pipelines require dense object annotations in training video sequences. In this work, we present Object-centric Prediction without Annotation (OPA), an object-centric video prediction method that takes advantage of priors from powerful computer vision models. We validate our method on a dataset comprised of video sequences of stacked objects falling, and demonstrate how to adapt a perception model in an environment through end-to-end video prediction training.
Recently, query based object detection frameworks achieve comparable performance with previous state-of-the-art object detectors. However, how to fully leverage such frameworks to perform instance segmentation remains an open problem. In this paper, we present QueryInst (Instances as Queries), a query based instance segmentation method driven by parallel supervision on dynamic mask heads. The key insight of QueryInst is to leverage the intrinsic one-to-one correspondence in object queries across different stages, as well as one-to-one correspondence between mask RoI features and object queries in the same stage. This approach eliminates the explicit multi-stage mask head connection and the proposal distribution inconsistency issues inherent in non-query based multi-stage instance segmentation methods. We conduct extensive experiments on three challenging benchmarks, i.e., COCO, CityScapes, and YouTube-VIS to evaluate the effectiveness of QueryInst in instance segmentation and video instance segmentation (VIS) task. Specifically, using ResNet-101-FPN backbone, QueryInst obtains 48.1 box AP and 42.8 mask AP on COCO test-dev, which is 2 points higher than HTC in terms of both box AP and mask AP, while runs 2.4 times faster. For video instance segmentation, QueryInst achieves the best performance among all online VIS approaches and strikes a decent speed-accuracy trade-off. Code is available at \url{https://github.com/hustvl/QueryInst}.