DPF: Learning Dense Prediction Fields with Weak Supervision

03/29/2023
by   Xiaoxue Chen, et al.
0

Nowadays, many visual scene understanding problems are addressed by dense prediction networks. But pixel-wise dense annotations are very expensive (e.g., for scene parsing) or impossible (e.g., for intrinsic image decomposition), motivating us to leverage cheap point-level weak supervision. However, existing pointly-supervised methods still use the same architecture designed for full supervision. In stark contrast to them, we propose a new paradigm that makes predictions for point coordinate queries, as inspired by the recent success of implicit representations, like distance or radiance fields. As such, the method is named as dense prediction fields (DPFs). DPFs generate expressive intermediate features for continuous sub-pixel locations, thus allowing outputs of an arbitrary resolution. DPFs are naturally compatible with point-level supervision. We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition. In these two cases, supervision comes in the form of single-point semantic category and two-point relative reflectance, respectively. As benchmarked by three large-scale public datasets PASCALContext, ADE20K and IIW, DPFs set new state-of-the-art performance on all of them with significant margins. Code can be accessed at https://github.com/cxx226/DPF.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 13

page 16

page 17

page 18

research
10/25/2022

Pointly-Supervised Panoptic Segmentation

In this paper, we propose a new approach to applying point-level annotat...
research
12/02/2022

Neural Radiance Fields for Manhattan Scenes with Unknown Manhattan Frame

Novel view synthesis and 3D modeling using implicit neural field represe...
research
09/04/2018

OCNet: Object Context Network for Scene Parsing

Context is essential for various computer vision tasks. The state-of-the...
research
11/04/2020

Multi-layer Feature Aggregation for Deep Scene Parsing Models

Scene parsing from images is a fundamental yet challenging problem in vi...
research
11/06/2018

Weakly Supervised Scene Parsing with Point-based Distance Metric Learning

Semantic scene parsing is suffering from the fact that pixel-level annot...
research
05/21/2021

Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Hidden features in neural network usually fail to learn informative repr...
research
12/16/2020

CompositeTasking: Understanding Images by Spatial Composition of Tasks

We define the concept of CompositeTasking as the fusion of multiple, spa...

Please sign up or login with your details

Forgot password? Click here to reset