# Implicit Label Augmentation on Partially Annotated Clips via Temporally-Adaptive Features Learning

## TL;DR

This paper introduces Temporally-Adaptive Features learning, a novel method that leverages partially annotated video clips to improve single frame model accuracy by applying temporal change constraints, outperforming prior techniques.

## Contribution

The paper proposes TAF, a new principled approach for implicit label augmentation using temporal constraints, enhancing single frame models from partially annotated clips.

## Key findings

- TAF improves semantic segmentation accuracy across multiple architectures.
- Empirical results show significant gains over previous methods.
- TAF generalizes slow feature learning with stronger empirical support.

## Abstract

Partially annotated clips contain rich temporal contexts that can complement the sparse key frame annotations in providing supervision for model training. We present a novel paradigm called Temporally-Adaptive Features (TAF) learning that can utilize such data to learn better single frame models. By imposing distinct temporal change rate constraints on different factors in the model, TAF enables learning from unlabeled frames using context to enhance model accuracy. TAF generalizes "slow feature" learning and we present much stronger empirical evidence than prior works, showing convincing gains for the challenging semantic segmentation task over a variety of architecture designs and on two popular datasets. TAF can be interpreted as an implicit label augmentation method but is a more principled formulation compared to existing explicit augmentation techniques. Our work thus connects two promising methods that utilize partially annotated clips for single frame model training and can inspire future explorations in this direction.