DETR++: Taming Your Multi-Scale Detection Transformer

2022-06-07 · Chi Zhang, Lijuan Liu, Xiaoxue Zang, Frederick Liu, Hao Zhang, Xinying Song, Jindong Chen

Convolutional Neural Networks (CNN) have dominated the field of detection ever since the success of AlexNet in ImageNet classification [12]. With the sweeping reform of Transformers [27] in natural language processing, Carion et al. [2] introduce the Transformer-based detection method, i.e., DETR. However, due to the quadratic complexity in the self-attention mechanism in the Transformer, DETR is never able to incorporate multi-scale features as performed in existing CNN-based detectors, leading to inferior results in small object detection. To mitigate this issue and further improve performance of DETR, in this work, we investigate different methods to incorporate multi-scale features and find that a Bi-directional Feature Pyramid (BiFPN) works best with DETR in further raising the detection precision. With this discovery, we propose DETR++, a new architecture that improves detection results by 1.9% AP on MS COCO 2017, 11.5% AP on RICO icon detection, and 9.1% AP on RICO layout extraction over existing baselines.

📄 PDF Abstract BibTeX arXiv:2206.02977

Code (0)

등록된 구현이 없습니다.

Tasks

object-detection Object Detection Small Object Detection

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Adam 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…

Taming Detection Transformers for Medical Object Detection

2023-06-27 · Marc K. Ickler, Michael Baumgartner, Saikat Roy, Tassilo Wald 외

The accurate detection of suspicious regions in medical images is an error-prone and time-consuming process required by many routinely performed diagnostic procedures. To support clinicians during this difficult task, se…

Diagnostic Medical Object Detection Object object-detection+1

Enhancing Your Trained DETRs with Box Refinement

2023-07-21 · Yiqun Chen, Qiang Chen, Peize Sun, Shoufa Chen 외

We present a conceptually simple, efficient, and general framework for localization problems in DETR-like models. We add plugins to well-trained models instead of inefficiently designing new models and training them from…

Cross Resolution Encoding-Decoding For Detection Transformers

2024-10-05 · Ashish Kumar, Jaesik Park

Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decodin…

object-detection Object Detection

M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers

2021-04-24 · Tianrui Guan, Jun Wang, Shiyi Lan, Rohan Chandra 외

We present a novel architecture for 3D object detection, M3DeTR, which combines different point cloud representations (raw, voxels, bird-eye view) with different feature scales based on multi-scale feature pyramids. M3De…

3D Object Detection object-detection Object Detection Relation

Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR

2023-03-13 · Feng Li, Ailing Zeng, Shilong Liu, Hao Zhang 외

Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance. Its success cannot be achieved without the re-introduction of multi-scale feature fusion in the encoder. However, the excessively inc…