Learning to Segment Object Candidates via Recursive Neural Networks

TL;DR

This paper introduces a recursive neural network-based method for generating object proposals that adaptively learns region merging and objectness measures, leading to high recall and accurate boundary preservation in object detection.

Contribution

The paper presents a novel deep architecture that hierarchically groups regions for object proposal generation, jointly learning similarity and objectness measures during the process.

Findings

Achieves high recall in object proposals on PASCAL VOC and ImageNet.

Outperforms existing methods in accuracy and efficiency.

Effectively preserves object boundaries during proposal generation.

Abstract

To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple yet effective approach for segmenting object proposals via a deep architecture of recursive neural networks (ReNNs), which hierarchically groups regions for detecting object candidates over scales. Unlike traditional methods that mainly adopt fixed similarity measures for merging regions or finding object proposals, our approach adaptively learns the region merging similarity and the objectness measure during the process of hierarchical region grouping. Specifically, guided by a structured loss, the ReNN model jointly optimizes the cross-region similarity metric with the region merging process as well as the objectness prediction. During inference of the object proposal generation, we introduce randomness into the greedy search to cope with the ambiguity of grouping regions. Extensive experiments on standard benchmarks, e.g., PASCAL VOC and ImageNet, suggest that our approach is capable of producing object proposals with high recall while well preserving the object boundaries and outperforms other existing methods in both accuracy and efficiency.