Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

FitVid: Overfitting in Pixel-Level Video Prediction

About

An agent that is capable of predicting what happens next can perform a variety of tasks through planning with no additional training. Furthermore, such an agent can internally represent the complex dynamics of the real-world and therefore can acquire a representation useful for a variety of visual perception tasks. This makes predicting the future frames of a video, conditioned on the observed past and potentially future actions, an interesting task which remains exceptionally challenging despite many recent advances. Existing video prediction models have shown promising results on simple narrow benchmarks but they generate low quality predictions on real-life datasets with more complicated dynamics or broader domain. There is a growing body of evidence that underfitting on the training data is one of the primary causes for the low quality predictions. In this paper, we argue that the inefficient use of parameters in the current video models is the main reason for underfitting. Therefore, we introduce a new architecture, named FitVid, which is capable of severe overfitting on the common benchmarks while having similar parameter count as the current state-of-the-art models. We analyze the consequences of overfitting, illustrating how it can produce unexpected outcomes such as generating high quality output by repeating the training data, and how it can be mitigated using existing image augmentation techniques. As a result, FitVid outperforms the current state-of-the-art models across four different video prediction benchmarks on four different metrics.

Mohammad Babaeizadeh, Mohammad Taghi Saffar, Suraj Nair, Sergey Levine, Chelsea Finn, Dumitru Erhan• 2021

Related benchmarks

TaskDatasetResultRank
Video PredictionBAIR (test)
FVD93.6
59
Video PredictionBAIR Robot Pushing
FVD93.6
38
Video PredictionBair
FVD93.6
34
Frame predictionBair
FVD94
15
Long-Context Video PredictionDMLab 64x64
FVD123
12
Video PredictionBAIR 64 x 64 1 -> 15
FVD93.6
11
Video PredictionRoboNet
FVD62.5
7
Flat blockVP2 benchmark
Mean Success Rate9.17
7
Green buttonVP2 benchmark
Mean Success Rate84
7
Video PredictionRoboNet (test)
FVD62.5
7
Showing 10 of 17 rows

Other info

Code

Follow for update