# End-to-End Integration of a Convolutional Network, Deformable Parts Model and Non-Maximum Suppression

Source: [End-to-End Integration of a Convolutional Network, Deformable Parts Model and Non-Maximum Suppression](<https://www.sota2.com/research/paper/68fa61961e209131ce9f4df4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:01:28.850Z

Authors: Li Wan, David Eigen, Rob Fergus

Published: 2014-11-19T18:36:09.000Z

## Abstract

Deformable Parts Models and Convolutional Networks each have achieved notable performance in object detection. Yet these two approaches find their strengths in complementary areas: DPMs are well-versed in object composition, modeling fine-grained spatial relationships between parts; likewise, ConvNets are adept at producing powerful image features, having been discriminatively trained directly on the pixels. In this paper, we propose a new model that combines these two approaches, obtaining the advantages of each. We train this model using a new structured loss function that considers all bounding boxes within an image, rather than isolated object instances. This enables the non-maximal suppression (NMS) operation, previously treated as a separate post-processing stage, to be integrated into the model. This allows for discriminative training of our combined Convnet + DPM + NMS model in end-to-end fashion. We evaluate our system on PASCAL VOC 2007 and 2011 datasets, achieving competitive results on both benchmarks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1411.5309>)

[PDF](<https://arxiv.org/pdf/1411.5309.pdf>)
