English
Related papers

Related papers: Disentangling Latent Embeddings with Sparse Linear…

200 papers

Semantic compression, a compression scheme where the distortion metric, typically MSE, is replaced with semantic fidelity metrics, tends to become more and more popular. Most recent semantic compression schemes rely on the foundation model…

Image and Video Processing · Electrical Eng. & Systems 2024-12-09 Tom Bachard , Thomas Maugey

Concept-based approaches, which aim to identify human-understandable concepts within a model's internal representations, are a promising method for interpreting embeddings from deep neural network models, such as CLIP. While these…

Machine Learning · Computer Science 2025-06-18 Jitian Zhao , Chenghui Li , Frederic Sala , Karl Rohe

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Haoxian Ruan , Zhihua Xu , Zhijing Yang , Yongyi Lu , Jinghui Qin , Tianshui Chen

Vision-language models, such as CLIP, have achieved significant success in aligning visual and textual representations, becoming essential components of many multi-modal large language models (MLLMs) like LLaVA and OpenFlamingo. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Shizhan Gong , Yankai Jiang , Qi Dou , Farzan Farnia

Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node. Many of the existing methods focus on obtaining a static vector…

Machine Learning · Computer Science 2021-04-28 Ping Wang , Khushbu Agarwal , Colby Ham , Sutanay Choudhury , Chandan K. Reddy

Visually grounded speech systems learn from paired images and their spoken captions. Recently, there have been attempts to utilize the visually grounded models trained from images and their corresponding text captions, such as CLIP, to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-12 Saurabhchand Bhati , Jesús Villalba , Laureano Moro-Velazquez , Thomas Thebaud , Najim Dehak

Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations. However, existing CBMs often suffer from input-to-concept mapping bias and limited controllability, which…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Gaoxiang Huang , Songning Lai , Yutao Yue

Monocular depth estimation involves predicting depth from a single RGB image and plays a crucial role in applications such as autonomous driving, robotic navigation, 3D reconstruction, etc. Recent advancements in learning-based methods have…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Jingming Xia , Guanqun Cao , Guang Ma , Yiben Luo , Qinzhao Li , John Oyekan

Vision-language models encode images and text in a joint space, minimizing the distance between corresponding image and text pairs. How are language and images organized in this joint space, and how do the models encode meaning and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Isabel Papadimitriou , Huangyuan Su , Thomas Fel , Sham Kakade , Stephanie Gil

We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs. Given that multiple image patches often correspond to single words, we…

Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Junjie Wang , Keyu Chen , Yulin Li , Bin Chen , Hengshuang Zhao , Xiaojuan Qi , Zhuotao Tian

Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information…

Computation and Language · Computer Science 2023-12-19 Vivi Nastase , Paola Merlo

Advances in multi-modal embeddings, and in particular CLIP, have recently driven several breakthroughs in Computer Vision (CV). CLIP has shown impressive performance on a variety of tasks, yet, its inherently opaque architecture may hinder…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Loris Giulivi , Giacomo Boracchi

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Fawaz Sammani , Nikos Deligiannis

Given unlabelled datasets containing both old and new categories, generalized category discovery (GCD) aims to accurately discover new classes while correctly classifying old classes. Current GCD methods only use a single visual modality of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Enguang Wang , Zhimao Peng , Zhengyuan Xie , Fei Yang , Xialei Liu , Ming-Ming Cheng

Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Wenbin He , William Surmeier , Arvind Kumar Shekar , Liang Gou , Liu Ren

The CLIP network measures the similarity between natural text and images; in this work, we investigate the entanglement of the representation of word images and natural images in its image encoder. First, we find that the image encoder has…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Joanna Materzynska , Antonio Torralba , David Bau

Learned image compression (LIC) techniques have achieved remarkable progress; however, effectively integrating high-level semantic information remains challenging. In this work, we present a \underline{S}emantic-\underline{E}nhanced…

Applications · Statistics 2025-04-03 Haisheng Fu , Jie Liang , Zhenman Fang , Jingning Han

Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on visual cues and implicitly capture local character…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Leeje Jang , Yijun Lin , Yao-Yi Chiang , Jerod Weinman

Most image-text retrieval work adopts binary labels indicating whether a pair of image and text matches or not. Such a binary indicator covers only a limited subset of image-text semantic relations, which is insufficient to represent…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Zheng Li , Caili Guo , Zerun Feng , Jenq-Neng Hwang , Ying Jin , Yufeng Zhang