# A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications

Source: [A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications](<https://www.sota2.com/research/paper/68fa6b641e209131cea2e069>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:48:06.915Z

Authors: Yun-Hao Cao, Jianxin Wu

Published: 2021-06-17T06:07:49.000Z

## Abstract

This paper starts by revealing a surprising finding: without any learning, a randomly initialized CNN can localize objects surprisingly well. That is, a CNN has an inductive bias to naturally focus on objects, named as Tobias ("The object is at sight") in this paper. This empirical inductive bias is further analyzed and successfully applied to self-supervised learning (SSL). A CNN is encouraged to learn representations that focus on the foreground object, by transforming every image into various versions with different backgrounds, where the foreground and background separation is guided by Tobias. Experimental results show that the proposed Tobias significantly improves downstream tasks, especially for object detection. This paper also shows that Tobias has consistent improvements on training sets of different sizes, and is more resilient to changes in image augmentations. Code is available at https://github.com/CupidJay/Tobias.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.09259>)

[PDF](<https://arxiv.org/pdf/2106.09259.pdf>)
