paper-with-me

Papers

CLIP4IDC: CLIP for Image Difference Captioning

2022-06-01 · Zixin Guo, Tzu-Jui Julius Wang, Jorma Laaksonen

Image Difference Captioning (IDC) aims at generating sentences to describe differences between two similar-looking images. Conventional approaches learn an IDC model with a pre-trained and usually frozen visual feature extractor. Accordingly, two major issues may arise: (1) a large domain gap usually exists between the pre-training datasets used for training such a visual encoder and that of the downstream IDC task, and (2) the visual feature extractor, when separately encoding two images, often does not effectively encode the visual changes between two images. Due to the excellent zero-shot performance of the recently proposed CLIP, we thus propose CLIP4IDC to transfer a CLIP model for the IDC task to address those issues. Different from directly fine-tuning CLIP to generate sentences, we introduce an adaptation training process to adapt CLIP's visual encoder to capture and align differences in image pairs based on the textual descriptions. Experiments on three IDC benchmark datasets, CLEVR-Change, Spot-the-Diff, and Image-Editing-Request, demonstrate the effectiveness of CLIP4IDC.

📄 PDF Abstract BibTeX arXiv:2206.00629

Code (1)

sushizixin/clip4idc 공식 구현 pytorch

Tasks

Domain AdaptationImage Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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 $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
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…

Similar Papers 제목 키워드 기반

Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement

2023-08-23 · Daiki Takeuchi, Yasunori Ohishi, Daisuke Niizumi, Noboru Harada 외

We proposed Audio Difference Captioning (ADC) as a new extension task of audio captioning for describing the semantic differences between input pairs of similar but slightly different audio clips. The ADC solves the prob…

Audio captioningDisentanglement

Text-Only Training for Image Captioning using Noise-Injected CLIP

2022-11-01 · David Nukrai, Ron Mokady, Amir Globerson

We consider the task of image-captioning using only the CLIP model and additional text data at training time, and no additional captioned images. Our approach relies on the fact that CLIP is trained to make visual and te…

DecoderImage CaptioningLanguage ModellingSemi Supervised Learning for Image Captioning

L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training

2025-07-11 · Li Li, Yingzhe Peng, Xu Yang, Ruoxi Cheng 외 arxiv

We propose a novel embedding-based captioning metric termed as L-CLIPScore that can be used for efficiently evaluating caption quality and training captioning model. L-CLIPScore is calculated from a lightweight CLIP (L-C…

Learning Audio-Video Modalities from Image Captions

2022-04-01 · Arsha Nagrani, Paul Hongsuck Seo, Bryan Seybold, Anja Hauth 외

A major challenge in text-video and text-audio retrieval is the lack of large-scale training data. This is unlike image-captioning, where datasets are in the order of millions of samples. To close this gap we propose a n…

Image CaptioningRetrievalVideo CaptioningVideo Retrieval+2

CLIPScore: A Reference-free Evaluation Metric for Image Captioning

2021-04-18 · EMNLP 2021 11 · Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras 외

Image captioning has conventionally relied on reference-based automatic evaluations, where machine captions are compared against captions written by humans. This is in contrast to the reference-free manner in which human…

Hallucination Pair-wise Detection (1-ref)Hallucination Pair-wise Detection (4-ref)Human Judgment ClassificationHuman Judgment Correlation+1