paper-with-me

Papers

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

2024-06-25 · Ye Won Byun, Cathy Jiao, Shahriar Noroozizadeh, Jimin Sun, Rosa Vitiello

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.

📄 PDF Abstract BibTeX arXiv:2406.17876

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음

Similar Papers 제목 키워드 기반

The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks

2024-05-14 · Carmela Calabrese, Stefano Berti, Giulia Pasquale, Lorenzo Natale

Addressing multi-label action recognition in videos represents a significant challenge for robotic applications in dynamic environments, especially when the robot is required to cooperate with humans in tasks that involv…

Action RecognitionAction Recognition In Videosimage-classificationImage Classification+2

CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection

2023-09-21 · NeurIPS 2023 11

Zero-shot Human-Object Interaction (HOI) detection aims to identify both seen and unseen HOI categories. A strong zero-shot HOI detector is supposed to be not only capable of discriminating novel interactions but also ro…

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation

2023-03-21 · CVPR 2024 1 · Seokju Cho, Heeseong Shin, Sunghwan Hong, Anurag Arnab 외

Open-vocabulary semantic segmentation presents the challenge of labeling each pixel within an image based on a wide range of text descriptions. In this work, we introduce a novel cost-based approach to adapt vision-langu…

Image SegmentationOpen Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentation+2

Unveiling Glitches: A Deep Dive into Image Encoding Bugs within CLIP

2024-06-30 · Ayush Ranjan, Daniel Wen, Karthik Bhat

Understanding the limitations and weaknesses of state-of-the-art models in artificial intelligence is crucial for their improvement and responsible application. In this research, we focus on CLIP, a model renowned for it…

HallucinationImage Comprehension

Seeing the Unseen: Visual Common Sense for Semantic Placement

2024-01-15 · CVPR 2024 1 · Ram Ramrakhya, Aniruddha Kembhavi, Dhruv Batra, Zsolt Kira 외

Computer vision tasks typically involve describing what is present in an image (e.g. classification, detection, segmentation, and captioning). We study a visual common sense task that requires understanding what is not p…

Common Sense ReasoningImage DescriptionObject