Rethinking Implicit Neural Representations for Vision Learners

TL;DR

This paper introduces a new Implicit Neural Representation Network (INRN) that extends the application of INRs from low-level tasks to high-level vision tasks like classification and detection, addressing previous limitations.

Contribution

It reformulates INR definitions and proposes INRN, enabling INRs to be effective for both low-level and high-level vision tasks, a novel approach in the field.

Findings

Effective on low-level tasks like image fitting

Achieves competitive results on high-level tasks

Demonstrates versatility of INRs across vision applications

Abstract

Implicit Neural Representations (INRs) are powerful to parameterize continuous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image generation. The questions on how to explore INRs to high-level tasks and deep networks are still under-explored. Existing INRs methods suffer from two problems: 1) narrow theoretical definitions of INRs are inapplicable to high-level tasks; 2) lack of representation capabilities to deep networks. Motivated by the above facts, we reformulate the definitions of INRs from a novel perspective and propose an innovative Implicit Neural Representation Network (INRN), which is the first study of INRs to tackle both low-level and high-level tasks. Specifically, we present three key designs for basic blocks in INRN along with two different stacking ways and corresponding loss functions. Extensive experiments with analysis on both low-level tasks (image fitting) and high-level vision tasks (image classification, object detection, instance segmentation) demonstrate the effectiveness of the proposed method.