English
Related papers

Related papers: Group Evidence Matters: Tiling-based Semantic Gati…

200 papers

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Yifei Liu , Mathias Gehrig , Nico Messikommer , Marco Cannici , Davide Scaramuzza

Recent vision-language foundation models still frequently produce outputs misaligned with their inputs, evidenced by object hallucination in captioning and prompt misalignment in the text-to-image generation model. Recent studies have…

Computer Vision and Pattern Recognition · Computer Science 2024-12-25 JeongYeon Nam , Jinbae Im , Wonjae Kim , Taeho Kil

In this paper, we address the problem of detecting small, dense, and overlapping objects, a major challenge in computer vision. Our focus is on reviewing proposed methods based on deep learning supervised approaches. We provide a detailed…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Oussama Messai , Abbass Zein-Eddine , Abdelouahid Bentamou , Mickael Picq , Nicolas Duquesne , Stéphane Puydarrieux , Yann Gavet

Many modern AI question-answering systems convert text into vectors and retrieve the closest matches to a user question. While effective for topical similarity, similarity scores alone do not explain why some retrieved text can serve as…

Computation and Language · Computer Science 2026-03-20 Victor P. Unda

Most salient object detection approaches use U-Net or feature pyramid networks (FPN) as their basic structures. These methods ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Xiaoqi Zhao , Youwei Pang , Lihe Zhang , Huchuan Lu , Lei Zhang

Self-supervised learning (SSL) faces a fundamental conflict between semantic understanding and image reconstruction. High-level semantic SSL (e.g., DINO) relies on global tokens that are forced to be location-invariant for augmentation…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Theodore Zhengde Zhao , Sid Kiblawi , Jianwei Yang , Naoto Usuyama , Reuben Tan , Noel C Codella , Tristan Naumann , Hoifung Poon , Mu Wei

Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial layout correlations among proposals are…

Computer Vision and Pattern Recognition · Computer Science 2016-08-19 Jianan Li , Xiaodan Liang , Jianshu Li , Tingfa Xu , Jiashi Feng , Shuicheng Yan

Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences. However, spatial and temporal cues are often unreliable in real-world…

Computer Vision and Pattern Recognition · Computer Science 2021-05-17 Peijia Chen , Jianhuang Lai , Guangcong Wang , Huajun Zhou

Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Madhukar Reddy Vongala , Saurabh Srivastava , Jana Košecká

Tabular reasoning benchmarks mix semantic inference, numerical computation, and brittle table formatting, yet evaluations for small models remain vulnerable to contamination, dataset artifacts, and retrieval failures. We propose GLEAN, a…

Databases · Computer Science 2026-03-04 Qizhi Wang

Strong gravitational lensing forms multiple, time delayed images of cosmological sources, with the "focal length" of the lens serving as a cosmological distance probe. Robust estimation of the time delay distance can tightly constrain the…

Cosmology and Nongalactic Astrophysics · Physics 2014-12-10 Alireza Hojjati , Eric V. Linder

Scaling large language models to long contexts is challenging due to the quadratic computational cost of full attention. Mitigation approaches include KV-cache selection or compression techniques. We instead provide an effective and…

Machine Learning · Computer Science 2026-04-24 Yuzhen Mao , Michael Y. Li , Emily B. Fox

Diffusion transformers have shown exceptional performance in visual generation but incur high computational costs. Token reduction techniques that compress models by sharing the denoising process among similar tokens have been introduced.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Haipeng Fang , Sheng Tang , Juan Cao , Enshuo Zhang , Fan Tang , Tong-Yee Lee

We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Mingrui Li , Shuhong Liu , Heng Zhou , Guohao Zhu , Na Cheng , Tianchen Deng , Hongyu Wang

It is possible to associate a highly constrained subset of relative 6 DoF poses between two 3D shapes, as long as the local surface orientation, the normal vector, is available at every surface point. Local shape features can be used to…

Computer Vision and Pattern Recognition · Computer Science 2018-08-29 Anders Glent Buch , Lilita Kiforenko , Dirk Kraft

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and…

Machine Learning · Computer Science 2026-05-06 Stephen J. Thomas

Machine learning models can greatly improve the search for strong gravitational lenses in imaging surveys by reducing the amount of human inspection required. In this work, we test the performance of supervised, semi-supervised, and…

Astrophysics of Galaxies · Physics 2023-08-17 Keerthi Vasan G. C. , Stephen Sheng , Tucker Jones , Chi Po Choi , James Sharpnack

LiDAR point clouds are fundamental to various applications, yet high-precision scans incur substantial storage and transmission overhead. Existing methods typically convert unordered points into hierarchical octree or voxel structures for…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Pengpeng Yu , Haoran Li , Runqing Jiang , Jing Wang , Liang Lin , Yulan Guo

This paper tackles two key challenges: detecting small, dense, and overlapping objects (a major hurdle in computer vision) and improving the quality of noisy images, especially those encountered in industrial environments. [1, 2]. Our focus…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Oussama Messai , Abbass Zein-Eddine , Abdelouahid Bentamou , Mickaël Picq , Nicolas Duquesne , Stéphane Puydarrieux , Yann Gavet

Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Jung Hwan Heo , Seyedarmin Azizi , Arash Fayyazi , Massoud Pedram