The design of the query is crucial for the performance of DETR and its variants. Each query consists of two components: a content part and a positional one. Traditionally, the content query is initialized with a zero or learnable embedding, lacking essential content information and resulting in sub-optimal performance. In this paper, we introduce a novel plug-and-play module, Self-Adaptive Content Query (SACQ), to address this limitation. The SACQ module utilizes features from the transformer encoder to generate content queries via self-attention pooling. This allows candidate queries to adapt to the input image, resulting in a more comprehensive content prior and better focus on target objects. However, this improved concentration poses a challenge for the training process that utilizes the Hungarian matching, which selects only a single candidate and suppresses other similar ones. To overcome this, we propose a query aggregation strategy to cooperate with SACQ. It merges similar predicted candidates from different queries, easing the optimization. Our extensive experiments on the COCO dataset demonstrate the effectiveness of our proposed approaches across six different DETR's variants with multiple configurations, achieving an average improvement of over 1.0 AP.
University of Science and Technology of China（中国科学技术大学）；University of Edinburgh（爱丁堡大学）；University of Adelaide（阿德莱德大学）
Transformer-based detectors (DETRs) are becoming popular for their simple framework, but the large model size and heavy time consumption hinder their deployment in the real world. While knowledge distillation (KD) can be an appealing technique to compress giant detectors into small ones for comparable detection performance and low inference cost. Since DETRs formulate object detection as a set prediction problem, existing KD methods designed for classic convolution-based detectors may not be directly applicable. In this paper, we propose DETRDistill, a novel knowledge distillation method dedic…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Detecting customized moments and highlights from videos given natural language (NL) user queries is an important but under-studied topic. One of the challenges in pursuing this direction is the lack of annotated data. To address this issue, we present the Query-based Video Highlights (QVHIGHLIGHTS) dataset. It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant momen…
Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders
University of Pittsburgh（匹兹堡大学）；University of California, Irvine（加州大学尔湾分校）；Stevens Institute of Technology（史蒂文斯理工学院）；Illinois Institute of Technology（伊利诺伊理工学院）；New York University（纽约大学）
Recent proposed DETR variants have made tremendous progress in various scenarios due to their streamlined processes and remarkable performance. However, the learned queries usually explore the global context to generate the final set prediction, resulting in redundant burdens and unfaithful results. More specifically, a query is commonly responsible for objects of different scales and positions, which is a challenge for the query itself, and will cause spatial resource competition among queries. To alleviate this issue, we propose Team DETR, which leverages query collaboration and position con…
In this paper, we propose a novel query design for the transformer-based object detection. In previous transformer-based detectors, the object queries are a set of learned embeddings. However, each learned embedding does not have an explicit physical meaning and we cannot explain where it will focus on. It is difficult to optimize as the prediction slot of each object query does not have a specific mode. In other words, each object query will not focus on a specific region. To solved these problems, in our query design, object queries are based on anchor points, which are widely used in CNN-ba…
DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection
School of Information Engineering, Beijing Institute of Graphic Communication（信息工程学院，北京印刷学院）；School of Computing and Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）；College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）
The Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；IDEA（IDEA研究院）
We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results from the instability of bipartite graph matching which causes inconsistent optimization goals in early training stages. To address this issue, except for the Hungarian loss, our method additionally feeds ground-truth bounding boxes with noises into Transformer decoder and trains the model to reconstruct the original boxes, which effectively reduces the bipartit…
Institute of Computing Technology (ICT), Chinese Academy of Sciences（中国科学院计算技术研究所）；Stanford University（斯坦福大学）；University of Chinese Academy of Sciences（中国科学院大学）；AI Lab, Lenovo Research（联想研究院人工智能实验室）；Lenovo Ltd.（联想集团有限公司）
Recently, the dominant DETR-based approaches apply central-concept spatial prior to accelerate Transformer detector convergency. These methods gradually refine the reference points to the center of target objects and imbue object queries with the updated central reference information for spatially conditional attention. However, centralizing reference points may severely deteriorate queries' saliency and confuse detectors due to the indiscriminative spatial prior. To bridge the gap between the reference points of salient queries and Transformer detectors, we propose SAlient Point-based DETR (S…
The Chinese University of Hong Kong（香港中文大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Although DETR-based 3D detectors can simplify the detection pipeline and achieve direct sparse predictions, their performance still lags behind dense detectors with post-processing for 3D object detection from point clouds. DETRs usually adopt a larger number of queries than GTs (e.g., 300 queries v.s. 40 objects in Waymo) in a scene, which inevitably incur many false positives during inference. In this paper, we propose a simple yet effective sparse 3D detector, named Query Contrast Voxel-DETR (ConQueR), to eliminate the challenging false positives, and achieve more accurate and sparser predi…
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）
In this paper, we are interested in Detection Transformer (DETR), an end-to-end object detection approach based on a transformer encoder-decoder architecture without hand-crafted postprocessing, such as NMS. Inspired by Conditional DETR, an improved DETR with fast training convergence, that presented box queries (originally called spatial queries) for internal decoder layers, we reformulate the object query into the format of the box query that is a composition of the embeddings of the reference point and the transformation of the box with respect to the reference point. This reformulation ind…
South China University of Technology（华南理工大学）；Pazhou Lab（琶洲实验室）；Tencent AI-Lab（腾讯人工智能实验室）
Human-Object Interaction (HOI) detection is a core task for high-level image understanding. Recently, Detection Transformer (DETR)-based HOI detectors have become popular due to their superior performance and efficient structure. However, these approaches typically adopt fixed HOI queries for all testing images, which is vulnerable to the location change of objects in one specific image. Accordingly, in this paper, we propose to enhance DETR's robustness by mining hard-positive queries, which are forced to make correct predictions using partial visual cues. First, we explicitly compose hard-po…
MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction
Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）
In this paper, we study the problem of visual grounding by considering both phrase extraction and grounding (PEG). In contrast to the previous phrase-known-at-test setting, PEG requires a model to extract phrases from text and locate objects from images simultaneously, which is a more practical setting in real applications. As phrase extraction can be regarded as a $1$D text segmentation problem, we formulate PEG as a dual detection problem and propose a novel DQ-DETR model, which introduces dual queries to probe different features from image and text for object prediction and phrase mask pred…
Tsinghua University（清华大学）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；Hong Kong University of Science and Technology（香港科技大学）；Peng Cheng Laboratory（鹏城实验室）
We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in Transformer decoders and dynamically updates them layer-by-layer. Using box coordinates not only helps using explicit positional priors to improve the query-to-feature similarity and eliminate the slow training convergence issue in DETR, but also allows us to modulate the positional attention map using the box width and height information. Such a design mak…
PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection
New York University（纽约大学）；Boise State University（博伊西州立大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Irvine（加州大学 Irvine 分校）；Illinois Institute of Technology（伊利诺伊理工学院）；University of Pittsburgh（匹兹堡大学）
Recently, video moment retrieval and highlight detection (MR/HD) are being spotlighted as the demand for video understanding is drastically increased. The key objective of MR/HD is to localize the moment and estimate clip-wise accordance level, i.e., saliency score, to the given text query. Although the recent transformer-based models brought some advances, we found that these methods do not fully exploit the information of a given query. For example, the relevance between text query and video contents is sometimes neglected when predicting the moment and its saliency. To tackle this issue, we…
Query Expansion (QE) is a well established method for improving retrieval metrics in image search applications. When using QE, the search is conducted on a new query vector, constructed using an aggregation function over the query and images from the database. Recent works gave rise to QE techniques in which the aggregation function is learned, whereas previous techniques were based on hand-crafted aggregation functions, e.g., taking the mean of the query's nearest neighbors. However, most QE methods have focused on aggregation functions that work directly over the query and its immediate near…
Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection
Multimedia Laboratory, The Chinese University of HongKong（香港中文大学多媒体实验室）；SenseTime Research（商汤科技研究院）；Centre for Perceptual and Interactive Intelligence Limited（感知与交互智能中心有限公司）；Shanghai AI Laboratory（上海人工智能实验室）
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；MEGVII Technology（旷视科技）
After DETR was proposed, this novel transformer-based detection paradigm which performs several cross-attentions between object queries and feature maps for predictions has subsequently derived a series of transformer-based detection heads. These models iterate object queries after each cross-attention. However, they don't renew the query position which indicates object queries' position information. Thus model needs extra learning to figure out the newest regions that query position should express and need more attention. To fix this issue, we propose the Guided Query Position (GQPos) method …
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…
Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection, which simplifies the model pipeline and obtains superior performance. Our framework is based on DETR, with the box regression head replaced with a points prediction head. The learning of points is more flexible, and the distribution of points can reflect the angle and size of the target rotated box. We further propose to decouple the query features into classif…
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…
OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
Harbin Institute of Technology（哈尔滨工业大学）；Shenzhen University（深圳大学）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology, Chongqing Research Institute（哈尔滨工业大学重庆研究院）；CECloud Computing Technology Co., Ltd（天翼云计算技术有限公司）
Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. …
Nanjing University（南京大学）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Hong Kong（香港大学）；NVIDIA（英伟达）；Caltech（加州理工学院）
Panoptic segmentation involves a combination of joint semantic segmentation and instance segmentation, where image contents are divided into two types: things and stuff. We present Panoptic SegFormer, a general framework for panoptic segmentation with transformers. It contains three innovative components: an efficient deeply-supervised mask decoder, a query decoupling strategy, and an improved post-processing method. We also use Deformable DETR to efficiently process multi-scale features, which is a fast and efficient version of DETR. Specifically, we supervise the attention modules in the mas…
LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（电子工程系，香港理工大学）；School of Mechanical Science and Engineering, Huazhong University of Science and Technology（机械科学与工程学院，华中科技大学）
FMRFT: Fusion Mamba and DETR for Query Time Sequence Intersection Fish Tracking
National Innovation Center for Digital Fishery（国家数字渔业创新中心）；Key Laboratory of Smart Farming Technologies for Aquatic Animal and Livestock, Ministry of Agriculture and Rural Affairs（农业农村部水产动物与畜禽智慧养殖技术重点实验室）；College of Information and Electrical Engineering, China Agricultural University（中国农业大学信息与电气工程学院）；College of Engineering, China Agricultural University（中国农业大学工学院）；Smart City College, Beijing Union University（北京联合大学智慧城市学院）
Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformer
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；Shanghai Jiao Tong University（上海交通大学）；University of Chinese Academy of Sciences（中国科学院大学）
