ECT: Fine-grained Edge Detection with Learned Cause Tokens

TL;DR

This paper introduces a transformer-based approach with learnable cause tokens for fine-grained edge detection, addressing limitations of prior convolutional methods and achieving state-of-the-art results on benchmark datasets.

Contribution

Proposes a novel two-stage transformer network with cause tokens for improved fine-grained edge detection, incorporating a cause-aware decoder and edge alignment loss.

Findings

Achieves new state-of-the-art on BSDS-RIND benchmark.

Effectively models long-range dependencies for edge cause identification.

Demonstrates improved consistency between generic and fine-grained edges.

Abstract

In this study, we tackle the challenging fine-grained edge detection task, which refers to predicting specific edges caused by reflectance, illumination, normal, and depth changes, respectively. Prior methods exploit multi-scale convolutional networks, which are limited in three aspects: (1) Convolutions are local operators while identifying the cause of edge formation requires looking at far away pixels. (2) Priors specific to edge cause are fixed in prediction heads. (3) Using separate networks for generic and fine-grained edge detection, and the constraint between them may be violated. To address these three issues, we propose a two-stage transformer-based network sequentially predicting generic edges and fine-grained edges, which has a global receptive field thanks to the attention mechanism. The prior knowledge of edge causes is formulated as four learnable cause tokens in a cause-aware decoder design. Furthermore, to encourage the consistency between generic edges and fine-grained edges, an edge aggregation and alignment loss is exploited. We evaluate our method on the public benchmark BSDS-RIND and several newly derived benchmarks, and achieve new state-of-the-art results. Our code, data, and models are publicly available at https://github.com/Daniellli/ECT.git.