English
Related papers

Related papers: The Rescue Effect: Spatio-Semantic Early Exit Bypa…

200 papers

Robust preprocessing is rarely quantified in deep-learning pipelines for low-dose CT (LDCT) lung cancer screening. We develop and validate Virtual-Eyes, a clinically motivated 16-bit CT quality-control pipeline, and measure its differential…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Md. Enamul Hoq , Linda Larson-Prior , Fred Prior

Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectively ignored. This failure arises because explicit prior imposition drives optimization…

Machine Learning · Computer Science 2026-05-18 Hazhir Aliahmadi , Irina Babayan , Greg van Anders

Large-scale language-vision pre-training models, such as CLIP, have achieved remarkable text-guided image morphing results by leveraging several unconditional generative models. However, existing CLIP-guided image morphing methods encounter…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Yeongtak Oh , Saehyung Lee , Uiwon Hwang , Sungroh Yoon

Traditional transformer-based semantic segmentation relies on quantized embeddings. However, our analysis reveals that autoencoder accuracy on segmentation mask using quantized embeddings (e.g. VQ-VAE) is 8% lower than continuous-valued…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Masud Ahmed , Zahid Hasan , Syed Arefinul Haque , Abu Zaher Md Faridee , Sanjay Purushotham , Suya You , Nirmalya Roy

Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance of deep neural networks. Sample selection is an effective way…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Chao Liang , Linchao Zhu , Humphrey Shi , Yi Yang

This paper addresses explainable AI (XAI) through the lens of Concept Bottleneck Models (CBMs) that do not require explicit concept annotations, relying instead on concepts extracted using CLIP in a zero-shot manner. We show that CLIP,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Rémi Kazmierczak , Steve Azzolin , Eloïse Berthier , Goran Frehse , Gianni Franchi

Large Audio Language Models (LALMs) have been widely applied in real-time scenarios, such as in-car assistants and online meeting comprehension. In practice, audio inputs are often corrupted by device and environmental noise, leading to…

Sound · Computer Science 2026-01-13 Yuanhe Zhang , Jiayu Tian , Yibo Zhang , Shilinlu Yan , Liang Lin , Zhenhong Zhou , Li Sun , Sen Su

Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially from real-world…

Sound · Computer Science 2026-04-21 HaeJun Yoo , Yongseop Shin , Insung Lee , Myoung-Wan Koo , Du-Seong Chang

Quantitative magnetic resonance imaging (qMRI) provides tissue-specific parameters vital for clinical diagnosis. Although simultaneous multi-parametric qMRI (MP-qMRI) technologies enhance imaging efficiency, robustly reconstructing qMRI…

Image and Video Processing · Electrical Eng. & Systems 2025-06-12 Haonan Zhang , Guoyan Lao , Yuyao Zhang , Hongjiang Wei

Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design choices and find three insights which simplify and improve RAE. First, we study a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jaskirat Singh , Boyang Zheng , Zongze Wu , Richard Zhang , Eli Shechtman , Saining Xie

Recent advances in learned image compression (LIC) have enabled practical deployments, spurring active research into image compression for machines and progressive coding schemes. However, their integration remains under-explored: prior…

Image and Video Processing · Electrical Eng. & Systems 2026-05-12 Jungwoo Kim , Jun-Hyuk Kim , Jong-Seok Lee

Randomized controlled trials (RCTs) are the gold standard for estimating heterogeneous treatment effects, yet they are often underpowered for detecting effect heterogeneity. Large observational studies (OS) can supplement RCTs for…

Machine Learning · Computer Science 2026-04-07 Amir Asiaee , Samhita Pal

Extending CLIP models to semantic segmentation remains challenging due to the misalignment between their image-level pre-training objectives and the pixel-level visual understanding required for dense prediction. While prior efforts have…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Jinxin Zhou , Jiachen Jiang , Zhihui Zhu

Numerous examples in the literature proved that deep learning models have the ability to work well with multimodal data. Recently, CLIP has enabled deep learning systems to learn shared latent spaces between images and text descriptions,…

Low-rank adaptation (LoRA) has achieved remarkable success in fine-tuning pre-trained vision transformers for various downstream tasks. Existing studies mainly focus on exploring more parameter-efficient strategies or more effective…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Zheng Liu , Jinchao Zhu , Gao Huang

Quantum error correction (QEC) promises to exponentially suppress qubit noise, but typically assumes spatially-uniform and temporally-constant noise rates. However, real quantum hardware exhibits variation in noise levels over time, which…

Quantum Physics · Physics 2026-05-08 Maxwell Poster , Jason Chadwick , Jonathan Mark Baker

Image denoising is essential for removing noise in images caused by electric device malfunctions or other factors during image acquisition. It ensures the preservation of image quality and accurate interpretation. Many convolutional…

Quantum Physics · Physics 2025-10-22 Tara Kit , Kimsay Pov , Kimleang Kea , Won-Du Chang , Hee Chul Park , Youngsun Han

Stuttering detection breaks down when disfluencies overlap. Existing parametric models struggle to distinguish complex, simultaneous disfluencies (e.g., a 'block' with a 'prolongation') due to the scarcity of these specific combinations in…

Machine Learning · Computer Science 2025-12-16 Guransh Singh , Md Shah Fahad

Pretrained cross-modal models, for instance, the most representative CLIP, have recently led to a boom in using pre-trained models for cross-modal zero-shot tasks, considering the generalization properties. However, we analytically discover…

Multimedia · Computer Science 2024-06-28 Hanyao Wang , Yibing Zhan , Liu Liu , Liang Ding , Yan Yang , Jun Yu

We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the notion of coarse-to-fine in computer vision, we leverage small…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Runze Li , Dahun Kim , Bir Bhanu , Weicheng Kuo