# ET tu, CLIP? Addressing Common Object Errors for Unseen Environments

Source: [ET tu, CLIP? Addressing Common Object Errors for Unseen Environments](<https://www.sota2.com/research/paper/68fa73e41e209131cea5ebb6>)

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

Data updated: 2025-10-26T02:58:03.881Z

Authors: Ye Won Byun, Cathy Jiao, Shahriar Noroozizadeh, Jimin Sun, Rosa Vitiello

Published: 2024-06-25T18:35:13.000Z

## Abstract

We introduce a simple method that employs pre-trained CLIP encoders to enhance model generalization in the ALFRED task. In contrast to previous literature where CLIP replaces the visual encoder, we suggest using CLIP as an additional module through an auxiliary object detection objective. We validate our method on the recently proposed Episodic Transformer architecture and demonstrate that incorporating CLIP improves task performance on the unseen validation set. Additionally, our analysis results support that CLIP especially helps with leveraging object descriptions, detecting small objects, and interpreting rare words.

## 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/2406.17876>)

[PDF](<https://arxiv.org/pdf/2406.17876.pdf>)
