# Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction

arXiv: https://arxiv.org/abs/1504.03293 · HTML: https://mlsanity.com/paper/1504.03293/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2015.

## Built on by (most cited first, 11 of 11)

- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [Humble Teachers Teach Better Students for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.10456/) (2021)
- [Gradient-Free Textual Inversion](https://mlsanity.com/paper/2304.05818/) (2023)
- [Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization](https://mlsanity.com/paper/2106.04335/) (2021)
- [Derivative-Free Reinforcement Learning: A Review](https://mlsanity.com/paper/2102.05710/) (2021)
- [Derivative-Free Optimization for Low-Rank Adaptation in Large Language Models](https://mlsanity.com/paper/2403.01754/) (2024)
- [Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models](https://mlsanity.com/paper/2405.08674/) (2024)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detection](https://mlsanity.com/paper/2403.09313/) (2024)
- [HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval](https://mlsanity.com/paper/2405.07524/) (2024)
- [RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View](https://mlsanity.com/paper/2110.00644/) (2021)

## Abstract (arXiv)

Object detection systems based on the deep convolutional neural network (CNN) have recently made ground- breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are discriminative for categorization, inaccurate localization is still a major source of error for detection. Building upon high-capacity CNN architectures, we address the localization problem by 1) using a search algorithm based on Bayesian optimization that sequentially proposes candidate regions for an object bounding box, and 2) training the CNN with a structured loss that explicitly penalizes the localization inaccuracy. In experiments, we demonstrated that each of the proposed methods improves the detection performance over the baseline method on PASCAL VOC 2007 and 2012 datasets. Furthermore, two methods are complementary and significantly outperform the previous state-of-the-art when combined.