paper-with-me

홈 › Papers

DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection

2023-04-14 · CVPR 2023 1 · Zongheng Tang, Yifan Sun, Si Liu, Yi Yang

This paper presents a DETR-based method for cross-domain weakly supervised object detection (CDWSOD), aiming at adapting the detector from source to target domain through weak supervision. We think DETR has strong potential for CDWSOD due to an insight: the encoder and the decoder in DETR are both based on the attention mechanism and are thus capable of aggregating semantics across the entire image. The aggregation results, i.e., image-level predictions, can naturally exploit the weak supervision for domain alignment. Such motivated, we propose DETR with additional Global Aggregation (DETR-GA), a CDWSOD detector that simultaneously makes "instance-level + image-level" predictions and utilizes "strong + weak" supervisions. The key point of DETR-GA is very simple: for the encoder / decoder, we respectively add multiple class queries / a foreground query to aggregate the semantics into image-level predictions. Our query-based aggregation has two advantages. First, in the encoder, the weakly-supervised class queries are capable of roughly locating the corresponding positions and excluding the distraction from non-relevant regions. Second, through our design, the object queries and the foreground query in the decoder share consensus on the class semantics, therefore making the strong and weak supervision mutually benefit each other for domain alignment. Extensive experiments on four popular cross-domain benchmarks show that DETR-GA significantly improves CSWSOD and advances the states of the art (e.g., 29.0% --> 79.4% mAP on PASCAL VOC --> Clipart_all dataset).

📄 PDF Abstract BibTeX arXiv:2304.07082

Code (0)

등록된 구현이 없습니다.

Tasks

Decoderobject-detectionObject DetectionWeakly Supervised Object Detection

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection

2025-09-27 · Ben Liang, Hongguang Wei, Yuan Liu, Bingwen Qiu 외 arxiv

Remote sensing object detection is a critical technology for real-world applications such as natural resource monitoring, traffic management, and UAV-based rescue. Detecting tiny objects in high-resolution aerial imagery…

Object Detection

BlocksecRT-DETR: Decentralized Privacy-Preserving and Token-Efficient Federated Transformer Learning for Secure Real-Time Object Detection in ITS

2026-01-19 · Mohoshin Ara Tahera, Sabbir Rahman, Shuvalaxmi Dass, Sharif Ullah 외 arxiv

Federated real-time object detection using transformers in Intelligent Transportation Systems (ITS) faces three major challenges: (1) missing-class non-IID data heterogeneity from geographically diverse traffic environme…

Real-Time Object Detection

DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection

2025-12-08 · Bo Gao, Jingcheng Tong, Xingsheng Chen, Han Yu 외 arxiv

Small object detection in complex scenes exposes a fundamental tension in neural network design: backbone attention distributes computation uniformly regardless of content, pyramid necks inflate activation magnitudes dur…

Small Object Detection

FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection

2026-07-06 · Aiwen Liu, Chengguang Zhu, Gang Wang, Dandan Zhu 외 arxiv

Small object detection (SOD) remains a challenging task in real-world applications. Despite recent advances, existing detectors remain limited by rigid processing that entangle spatial aggregation with implicit frequency…

Small Object Detection

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

2022-07-22 · Sunghwan Hong, Seokju Cho, Jisu Nam, Stephen Lin 외

This paper presents a novel cost aggregation network, called Volumetric Aggregation with Transformers (VAT), for few-shot segmentation. The use of transformers can benefit correlation map aggregation through self-attenti…

DecoderFew-Shot Semantic SegmentationInductive BiasSemantic correspondence