Papers › Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade

Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade

5 Apr 2017CVPR 2017 7arXiv:1704.01344archive 2025-07-28

Xiaoxiao Li, Ziwei Liu, Ping Luo, Chen Change Loy, Xiaoou Tang

We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a cascade of several sub-models. Earlier sub-models are trained to handle easy and confident regions, and they progressively feed-forward harder regions to the next sub-model for processing. Convolutions are only calculated on these regions to reduce computations. The proposed method possesses several advantages. First, LC classifies most of the easy regions in the shallow stage and makes deeper stage focuses on a few hard regions. Such an adaptive and 'difficulty-aware' learning improves segmentation performance. Second, LC accelerates both training and testing of deep network thanks to early decisions in the shallow stage. Third, in comparison to MC, LC is an end-to-end trainable framework, allowing joint learning of all sub-models. We evaluate our method on PASCAL VOC and Cityscapes datasets, achieving state-of-the-art performance and fast speed.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

liuziwei7/region-conv mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AllSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation PASCAL VOC 2012 test Deep Layer Cascade (LC) Mean IoU 82.7% #23 of 51 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections