Dense Object Detection Based on De-Homogenized Queries

2024-06-13

Electronics

AI Summary

Query-based end-to-end detectors (e.g., DETR) suffer from duplicated predictions and missed detections in dense scenes due to query homogenization. Method: This paper proposes a query de-homogenization framework: (i) a learnable differentiated query encoding mechanism to decouple query representations; (ii) replacement of redundant encoder self-attention with lightweight inter-query communication guided by differentiated information; and (iii) relocation of the joint localization-confidence loss to the encoder output to optimize query initialization. Results: Our method achieves 93.6% AP, 39.2% MR⁻², and 84.3% JI on CrowdHuman—outperforming state-of-the-art methods including Iter-E2EDet and MIP. It reduces parameter count by ~8% compared to Deformable DETR, yielding a more robust, concise, and efficient end-to-end dense detection paradigm.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Dense object detection is widely used in automatic driving, video surveillance, and other fields. This paper focuses on the challenging task of dense object detection. Currently, detection methods based on greedy algorithms, such as non-maximum suppression (NMS), often produce many repetitive predictions or missed detections in dense scenarios, which is a common problem faced by NMS-based algorithms. Through the end-to-end DETR (DEtection TRansformer), as a type of detector that can incorporate the post-processing de-duplication capability of NMS, etc., into the network, we found that homogeneous queries in the query-based detector lead to a reduction in the de-duplication capability of the network and the learning efficiency of the encoder, resulting in duplicate prediction and missed detection problems. To solve this problem, we propose learnable differentiated encoding to de-homogenize the queries, and at the same time, queries can communicate with each other via differentiated encoding information, replacing the previous self-attention among the queries. In addition, we used joint loss on the output of the encoder that considered both location and confidence prediction to give a higher-quality initialization for queries. Without cumbersome decoder stacking and guaranteeing accuracy, our proposed end-to-end detection framework was more concise and reduced the number of parameters by about 8% compared to deformable DETR. Our method achieved excellent results on the challenging CrowdHuman dataset with 93.6% average precision (AP), 39.2% MR−2, and 84.3% JI. The performance overperformed previous SOTA methods, such as Iter-E2EDet (Progressive End-to-End Object Detection) and MIP (One proposal, Multiple predictions). In addition, our method is more robust in various scenarios with different densities.

Problem

• Addresses duplicate predictions in dense object detection.
• Improves de-duplication capability via differentiated encoding.
• Reduces parameters while maintaining detection accuracy.

Innovation

• De-homogenized queries enhance detection
• Differentiated encoding replaces self-attention
• Joint loss improves query initialization