English
Related papers

Related papers: Hallucination Improves the Performance of Unsuperv…

200 papers

Contrastive methods have led a recent surge in the performance of self-supervised representation learning (SSL). Recent methods like BYOL or SimSiam purportedly distill these contrastive methods down to their essence, removing bells and…

Machine Learning · Computer Science 2022-11-03 Alexander C. Li , Alexei A. Efros , Deepak Pathak

Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Xinlei Chen , Kaiming He

Although multimodal large language models (MLLMs) exhibit remarkable reasoning capabilities on complex multimodal understanding tasks, they still suffer from the notorious hallucination issue: generating outputs misaligned with obvious…

Machine Learning · Computer Science 2025-11-04 Wei Chen , Xin Yan , Bin Wen , Fan Yang , Tingting Gao , Di Zhang , Long Chen

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help…

Computer Vision and Pattern Recognition · Computer Science 2018-04-04 Yu-Xiong Wang , Ross Girshick , Martial Hebert , Bharath Hariharan

Recent self-supervised contrastive learning methods greatly benefit from the Siamese structure that aims at minimizing distances between positive pairs. For high performance Siamese representation learning, one of the keys is to design good…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Xiangyu Peng , Kai Wang , Zheng Zhu , Mang Wang , Yang You

Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely unknown if the nature of the representations induced by the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Rohit Gupta , Naveed Akhtar , Ajmal Mian , Mubarak Shah

Contrastive learning has recently demonstrated superior performance to supervised learning, despite requiring no training labels. We explore how contrastive learning can be applied to hundreds of thousands of unlabeled Mars terrain images,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Isaac Ronald Ward , Charles Moore , Kai Pak , Jingdao Chen , Edwin Goh

Despite the rapid success of Large Vision-Language Models (LVLMs), a persistent challenge is their tendency to generate hallucinated content, undermining reliability in real-world use. Existing training-free methods address hallucinations…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Neeraj Anand , Samyak Jha , Udbhav Bamba , Rahul Rahaman

Graph representation learning plays a vital role in processing graph-structured data. However, prior arts on graph representation learning heavily rely on labeling information. To overcome this problem, inspired by the recent success of…

Machine Learning · Computer Science 2021-07-19 Ming Jin , Yizhen Zheng , Yuan-Fang Li , Chen Gong , Chuan Zhou , Shirui Pan

Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learning. This work presents Masked Contrastive Representation…

Computer Vision and Pattern Recognition · Computer Science 2022-11-14 Yuchong Yao , Nandakishor Desai , Marimuthu Palaniswami

Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. We introduce HICD, a novel method designed to induce hallucinations for contrastive decoding to mitigate…

Computation and Language · Computer Science 2025-05-26 Xinyan Jiang , Hang Ye , Yongxin Zhu , Xiaoying Zheng , Zikang Chen , Jun Gong

Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often…

Computer Vision and Pattern Recognition · Computer Science 2021-10-28 Sangwoo Mo , Hyunwoo Kang , Kihyuk Sohn , Chun-Liang Li , Jinwoo Shin

Multimodal Large Language Models (MLLMs) have shown impressive perception and reasoning capabilities, yet they often suffer from hallucinations -- generating outputs that are linguistically coherent but inconsistent with the context of the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Bingkui Tong , Jiaer Xia , Kaiyang Zhou

Recent self-supervised contrastive learning methods greatly benefit from the Siamese structure that aims to minimizing distances between positive pairs. These methods usually apply random data augmentation to input images, expecting the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Sheng Wang , Zixu Zhuang , Xi Ouyang , Lichi Zhang , Zheren Li , Chong Ma , Tianming Liu , Dinggang Shen , Qian Wang

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

Machine Learning · Computer Science 2022-03-01 Nikunj Saunshi , Jordan Ash , Surbhi Goel , Dipendra Misra , Cyril Zhang , Sanjeev Arora , Sham Kakade , Akshay Krishnamurthy

Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Zhiyang Chen , Yousong Zhu , Yufei Zhan , Zhaowen Li , Chaoyang Zhao , Jinqiao Wang , Ming Tang

Large Vision-Language Models have shown strong multimodal reasoning capabilities, yet they remain susceptible to object hallucinations when language priors dominate insufficient or misaligned visual evidence. Training-free contrastive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Xiaoyi Huang , Kejia Zhang , Zhiming Luo

While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck, hindering their real-world deployments. Existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Fushuo Huo , Wenchao Xu , Zhong Zhang , Haozhao Wang , Zhicheng Chen , Peilin Zhao

Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual information, the choice of visual encoder is pivotal. We…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Weihang Wang , Xinhao Li , Ziyue Wang , Yan Pang , Jielei Zhang , Peiyi Li , Qiang Zhang , Longwen Gao

Hallucinations in Large Language Models (LLMs) -- generations that are plausible but factually unfaithful -- remain a critical barrier to high-stakes deployment. Current detection methods typically rely on computationally expensive external…

Artificial Intelligence · Computer Science 2026-01-23 Manish Bhatt