Previous object detectors make predictions based on dense grid points or numerous preset anchors. Most of these detectors are trained with one-to-many label assignment strategies. On the contrary, recent query-based object detectors depend on a sparse set of learnable queries and a series of decoder layers. The one-to-one label assignment is independently applied on each layer for the deep supervision during training. Despite the great success of query-based object detection, however, this one-to-one label assignment strategy demands the detectors to have strong fine-grained discrimination and modeling capacity. To solve the above problems, in this paper, we propose a new query-based object detector with cross-stage interaction, coined as StageInteractor. During the forward propagation, we come up with an efficient way to improve this modeling ability by reusing dynamic operators with lightweight adapters. As for the label assignment, a cross-stage label assigner is applied subsequent to the one-to-one label assignment. With this assigner, the training target class labels are gathered across stages and then reallocated to proper predictions at each decoder layer. On MS COCO benchmark, our model improves the baseline by 2.2 AP, and achieves 44.8 AP with ResNet-50 as backbone, 100 queries and 12 training epochs. With longer training time and 300 queries, StageInteractor achieves 51.1 AP and 52.2 AP with ResNeXt-101-DCN and Swin-S, respectively.
This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two limitations: lack of training emphasis and cascading errors from decoding sequence. We design and present Selective Query Recollection (SQR), a simple and effective training strategy for query-based object detectors. It cumulatively collects intermediate queries as decoding stages go deeper and selectively forwards the queries to the downstream stages aside…
Huazhong University of Science & Technology（华中科技大学）
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…
Vision Transformers have achieved state-of-the-art performance in many visual tasks. Due to the quadratic computational and memory complexities of self-attention, recent works either apply attention only to low-resolution inputs or restrict the receptive field to a small local region. To overcome these limitations, we propose key-only attention, which excludes query-key pairwise interactions and uses a compute-efficient saliency-gate to obtain attention weights, modeling local-global interactions in all stages. Key-only attention has linear computational and memory complexities w.r.t input siz…
Huazhong University of Science & Technology（华中科技大学）；Horizon Robotics（地平线机器人）
The query mechanism introduced in the DETR method is changing the paradigm of object detection and recently there are many query-based methods have obtained strong object detection performance. However, the current query-based detection pipelines suffer from the following two issues. Firstly, multi-stage decoders are required to optimize the randomly initialized object queries, incurring a large computation burden. Secondly, the queries are fixed after training, leading to unsatisfying generalization capability. To remedy the above issues, we present featurized object queries predicted by a qu…
Human-object interaction (HOI) detection as a downstream of object detection tasks requires localizing pairs of humans and objects and extracting the semantic relationships between humans and objects from an image. Recently, one-stage approaches have become a new trend for this task due to their high efficiency. However, these approaches focus on detecting possible interaction points or filtering human-object pairs, ignoring the variability in the location and size of different objects at spatial scales. To address this problem, we propose a transformer-based method, QAHOI (Query-Based Anchors…
University of Rochester（罗切斯特大学）；Tencent AI Lab（腾讯人工智能实验室）
We improve one-stage visual grounding by addressing current limitations on grounding long and complex queries. Existing one-stage methods encode the entire language query as a single sentence embedding vector, e.g., taking the embedding from BERT or the hidden state from LSTM. This single vector representation is prone to overlooking the detailed descriptions in the query. To address this query modeling deficiency, we propose a recursive sub-query construction framework, which reasons between image and query for multiple rounds and reduces the referring ambiguity step by step. We show our new …
Recently, two-stage Deformable DETR introduced the query-based two-stage head, a new type of two-stage head different from the region-based two-stage heads of classical detectors as Faster R-CNN. In query-based two-stage heads, the second stage selects one feature per detection processed by a transformer, called the query, as opposed to pooling a rectangular grid of features processed by CNNs as in region-based detectors. In this work, we improve the query-based head by improving the prior of the cross-attention operation with anchors, significantly speeding up the convergence while increasing…
3D point cloud understanding is an important component in autonomous driving and robotics. In this paper, we present a novel Embedding-Querying paradigm (EQ- Paradigm) for 3D understanding tasks including detection, segmentation, and classification. EQ-Paradigm is a unified paradigm that enables the combination of any existing 3D backbone architectures with different task heads. Under the EQ-Paradigm, the input is firstly encoded in the embedding stage with an arbitrary feature extraction architecture, which is independent of tasks and heads. Then, the querying stage enables the encoded featur…
Zhejiang University（浙江大学）；Nanyang Technological University（南洋理工大学）；Hong Kong University of Science and Technology（香港科技大学）
The prevailing framework for matching multimodal inputs is based on a two-stage process: 1) detecting proposals with an object detector and 2) matching text queries with proposals. Existing two-stage solutions mostly focus on the matching step. In this paper, we argue that these methods overlook an obvious \emph{mismatch} between the roles of proposals in the two stages: they generate proposals solely based on the detection confidence (i.e., query-agnostic), hoping that the proposals contain all instances mentioned in the text query (i.e., query-aware). Due to this mismatch, chances are that p…
PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization
University of North Texas（北卡罗来纳州立大学）；University of Texas at Dallas（德克萨斯大学达拉斯分校）；U.S. Naval Research Laboratory（美国海军研究实验室）；Brookhaven National Laboratory（布鲁克海文国家实验室）
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 mig…
Shanghai Jiao Tong University（上海交通大学）；Heriot-Watt University Malaysia（赫瑞-瓦特大学马来西亚校区）；Huawei Cloud（华为云）
Few-shot action recognition aims to recognize novel action classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradigm, which learns to compare the similarity between videos. Recently, it has been observed that directly measuring this similarity is not ideal since different action instances may show distinctive temporal distribution, resulting in severe misalignment issues across query and support videos. In this paper, we arrest this problem from two distinct aspects -- action duration misalignment and action evolution misalignmen…
BUPT（北京邮电大学）；ByteDance Inc.（字节跳动公司）；OPPO Research Institute（OPPO研究院）
We propose a sparse end-to-end multi-person pose regression framework, termed QueryPose, which can directly predict multi-person keypoint sequences from the input image. The existing end-to-end methods rely on dense representations to preserve the spatial detail and structure for precise keypoint localization. However, the dense paradigm introduces complex and redundant post-processes during inference. In our framework, each human instance is encoded by several learnable spatial-aware part-level queries associated with an instance-level query. First, we propose the Spatial Part Embedding Gener…
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…
Harbin Institute of Technology at Shenzhen（哈尔滨工业大学（深圳））；Tencent（腾讯）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）
Despite the remarkable success of existing methods for few-shot segmentation, there remain two crucial challenges. First, the feature learning for novel classes is suppressed during the training on base classes in that the novel classes are always treated as background. Thus, the semantics of novel classes are not well learned. Second, most of existing methods fail to consider the underlying semantic gap between the support and the query resulting from the representative bias by the scarce support samples. To circumvent these two challenges, we propose to activate the discriminability of novel…
Query expansion is a popular method to improve the quality of image retrieval with both conventional and CNN representations. It has been so far limited to global image similarity. This work focuses on diffusion, a mechanism that captures the image manifold in the feature space. The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches. An efficient off-line stage allows optional reduction in the number of stored regions. In the on-line stage, the proposed handling of unseen queries in the indexing stage remove…
Nanjing University（南京大学）；Shanghai AI Lab（上海人工智能实验室）
Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection paradigm requires multi-stage training and inference, and cannot capture context information outside the bounding box. Recently, a few query-based action detectors are proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and decoding, thus suffering from the issues of inferior performance or …
The University of Sydney（悉尼大学）；SenseTime, Inc.（商汤科技）
Few-shot segmentation focuses on the generalization of models to segment unseen object instances with limited training samples. Although tremendous improvements have been achieved, existing methods are still constrained by two factors. (1) The information interaction between query and support images is not adequate, leaving intra-class gap. (2) The object categories at the training and inference stages have no overlap, leaving the inter-class gap. Thus, we propose a framework, BriNet, to bridge these gaps. First, more information interactions are encouraged between the extracted features of th…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；NEC Laboratories America, Inc.（NEC美国实验室）
Self-supervised video representation learning has been shown to effectively improve downstream tasks such as video retrieval and action recognition. In this paper, we present the Cascade Positive Retrieval (CPR) that successively mines positive examples w.r.t. the query for contrastive learning in a cascade of stages. Specifically, CPR exploits multiple views of a query example in different modalities, where an alternative view may help find another positive example dissimilar in the query view. We explore the effects of possible CPR configurations in ablations including the number of mining s…
Indian Institute of Technology, Roorkee（印度理工学院鲁尔基分校）；Indian Statistical Institute（印度统计研究所）；University of Technology Sydney（悉尼科技大学）；Griffith University（格里菲斯大学）
An end-to-end architecture for multi-script document retrieval using handwritten signatures is proposed in this paper. The user supplies a query signature sample and the system exclusively returns a set of documents that contain the query signature. In the first stage, a component-wise classification technique separates the potential signature components from all other components. A bag-of-visual-words powered by SIFT descriptors in a patch-based framework is proposed to compute the features and a Support Vector Machine (SVM)-based classifier was used to separate signatures from the documents.…
Institute of High Performance Computing, A*STAR（A*STAR高性能计算研究所）；Nanyang Technological University（南洋理工大学）
Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature. Such a formulation does not treat each word of a query sentence on par when modeling language to visual attention, therefore prone to neglect words which are less important for sentence embedding but critical for visual grounding. In this paper we propose Word2Pix: a one-stage visual grounding network based on encoder-decoder transformer architecture that enables learning for textual to visual feature correspondence via word to pixel attention. The embe…
EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR（香港理工大学电子与电气工程系）；Division of Emerging Interdisciplinary Areas (EMIA), The Hong Kong University of Science and Technology, Hong Kong SAR（香港理工大学新兴跨学科领域研究中心）
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague（布拉格捷克理工大学捷克信息学、机器人与控制论研究所）
We present a Visual Place Recognition system that follows the two-stage format common to image retrieval pipelines. The system encodes images of places by employing the activations of different layers of a pre-trained, off-the-shelf, VGG16 Convolutional Neural Network (CNN) architecture. In the first stage of our method and given a query image of a place, a number of top candidate images is retrieved from a previously stored database of places. In the second stage, we propose an exhaustive comparison of the query image against these candidates by encoding semantic and spatial information in th…
Query-based moment retrieval aims to localize the most relevant moment in an untrimmed video according to the given natural language query. Existing works often only focus on one aspect of this emerging task, such as the query representation learning, video context modeling or multi-modal fusion, thus fail to develop a comprehensive system for further performance improvement. In this paper, we introduce a novel Cross-Modal Interaction Network (CMIN) to consider multiple crucial factors for this challenging task, including (1) the syntactic structure of natural language queries; (2) long-range …
University of Southern California（南加州大学）；Facebook Inc.（脸书公司）
A phrase grounding system localizes a particular object in an image referred to by a natural language query. In previous work, the phrases were restricted to have nouns that were encountered in training, we extend the task to Zero-Shot Grounding(ZSG) which can include novel, "unseen" nouns. Current phrase grounding systems use an explicit object detection network in a 2-stage framework where one stage generates sparse proposals and the other stage evaluates them. In the ZSG setting, generating appropriate proposals itself becomes an obstacle as the proposal generator is trained on the entities…
Computing similarity between a query and a document is fundamental in any information retrieval system. In search engines, computing query-document similarity is an essential step in both retrieval and ranking stages. In eBay search, document is an item and the query-item similarity can be computed by comparing different facets of the query-item pair. Query text can be compared with the text of the item title. Likewise, a category constraint applied on the query can be compared with the listing category of the item. However, images are one signal that are usually present in the items but are n…
