The reviewed record of science sign in
Pith

arxiv: 2105.13351 · v2 · pith:XAIN5X7O · submitted 2021-05-27 · cs.CV · cs.AI

Tracking Without Re-recognition in Humans and Machines

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:XAIN5X7Orecord.jsonopen to challenge →

classification cs.CV cs.AI
keywords trackingobjectvisualchallengecircuithumanmodelobjects
0
0 comments X
read the original abstract

Imagine trying to track one particular fruitfly in a swarm of hundreds. Higher biological visual systems have evolved to track moving objects by relying on both appearance and motion features. We investigate if state-of-the-art deep neural networks for visual tracking are capable of the same. For this, we introduce PathTracker, a synthetic visual challenge that asks human observers and machines to track a target object in the midst of identical-looking "distractor" objects. While humans effortlessly learn PathTracker and generalize to systematic variations in task design, state-of-the-art deep networks struggle. To address this limitation, we identify and model circuit mechanisms in biological brains that are implicated in tracking objects based on motion cues. When instantiated as a recurrent network, our circuit model learns to solve PathTracker with a robust visual strategy that rivals human performance and explains a significant proportion of their decision-making on the challenge. We also show that the success of this circuit model extends to object tracking in natural videos. Adding it to a transformer-based architecture for object tracking builds tolerance to visual nuisances that affect object appearance, resulting in a new state-of-the-art performance on the large-scale TrackingNet object tracking challenge. Our work highlights the importance of building artificial vision models that can help us better understand human vision and improve computer vision.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.