Visual Chunking: A List Prediction Framework for Region-Based Object Detection

TL;DR

This paper introduces visual chunking, a list prediction framework for region-based object detection that iteratively selects candidate regions, optimizing detection performance and outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel list prediction framework called visual chunking, with efficient algorithms for region proposal and learning-based prediction, advancing object detection techniques.

Findings

Outperforms baseline methods on benchmark datasets.

Efficient near-linear time region proposal algorithm.

Effective learning approaches for novel image prediction.

Abstract

We consider detecting objects in an image by iteratively selecting from a set of arbitrarily shaped candidate regions. Our generic approach, which we term visual chunking, reasons about the locations of multiple object instances in an image while expressively describing object boundaries. We design an optimization criterion for measuring the performance of a list of such detections as a natural extension to a common per-instance metric. We present an efficient algorithm with provable performance for building a high-quality list of detections from any candidate set of region-based proposals. We also develop a simple class-specific algorithm to generate a candidate region instance in near-linear time in the number of low-level superpixels that outperforms other region generating methods. In order to make predictions on novel images at testing time without access to ground truth, we develop learning approaches to emulate these algorithms' behaviors. We demonstrate that our new approach outperforms sophisticated baselines on benchmark datasets.