Corner2Net: Detecting Objects as Cascade Corners

TL;DR

Corner2Net introduces a novel cascade corner framework for object detection that improves accuracy and speed by eliminating heuristic corner matching and enhancing instance context understanding.

Contribution

It proposes a cascade corner pipeline that predicts corner pairs progressively, decouples corner localization from classification, and simplifies the search space for better detection performance.

Findings

Outperforms existing corner-based detectors on COCO in accuracy.

Achieves faster detection speeds with high accuracy.

Easily integrates with popular backbones like ResNeXt.

Abstract

The corner-based detection paradigm enjoys the potential to produce high-quality boxes. But the development is constrained by three factors: 1) Hard to match corners. Heuristic corner matching algorithms can lead to incorrect boxes, especially when similar-looking objects co-occur. 2) Poor instance context. Two separate corners preserve few instance semantics, so it is difficult to guarantee getting both two class-specific corners on the same heatmap channel. 3) Unfriendly backbone. The training cost of the hourglass network is high. Accordingly, we build a novel corner-based framework, named Corner2Net. To achieve the corner-matching-free manner, we devise the cascade corner pipeline which progressively predicts the associated corner pair in two steps instead of synchronously searching two independent corners via parallel heads. Corner2Net decouples corner localization and object classification. Both two corners are class-agnostic and the instance-specific bottom-right corner further simplifies its search space. Meanwhile, RoI features with rich semantics are extracted for classification. Popular backbones (e.g., ResNeXt) can be easily connected to Corner2Net. Experimental results on COCO show Corner2Net surpasses all existing corner-based detectors by a large margin in accuracy and speed.