Contrastive MIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning

• URL: http://arxiv.org/abs/2502.19642v2
• Date: Mon, 08 Sep 2025 17:17:17 GMT
• Title: Contrastive MIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning
• Authors: Micha Livne,
• Abstract summary: We introduce the contrastive Mutual Information Machine (cMIM), a probabilistic framework that augments the Mutual Information Machine (MIM) with a novel contrastive objective.<n> cMIM addresses this limitation by enforcing global discriminative structure while retaining MIM's generative strengths.<n>We present two main contributions: (1) we propose cMIM, a contrastive extension of MIM that eliminates the need for positive data augmentation and is robust to batch size, unlike InfoNCE-based methods; (2) we introduce informative embeddings, a general technique for extracting enriched representations from encoder--decoder
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Learning representations that generalize well to unknown downstream tasks is a central challenge in representation learning. Existing approaches such as contrastive learning, self-supervised masking, and denoising auto-encoders address this challenge with varying trade-offs. In this paper, we introduce the {contrastive Mutual Information Machine} (cMIM), a probabilistic framework that augments the Mutual Information Machine (MIM) with a novel contrastive objective. While MIM maximizes mutual information between inputs and latent variables and encourages clustering of latent codes, its representations underperform on discriminative tasks compared to state-of-the-art alternatives. cMIM addresses this limitation by enforcing global discriminative structure while retaining MIM's generative strengths. We present two main contributions: (1) we propose cMIM, a contrastive extension of MIM that eliminates the need for positive data augmentation and is robust to batch size, unlike InfoNCE-based methods; (2) we introduce {informative embeddings}, a general technique for extracting enriched representations from encoder--decoder models that substantially improve discriminative performance without additional training, and which apply broadly beyond MIM. Empirical results demonstrate that cMIM consistently outperforms MIM and InfoNCE in classification and regression tasks, while preserving comparable reconstruction quality. These findings suggest that cMIM provides a unified framework for learning representations that are simultaneously effective for discriminative and generative applications.

Related papers

• CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension [49.6969505536365]
  We propose CREM, with a unified framework that enhances multimodal representations for retrieval while preserving generative ability.<n>CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T08:09:51Z)
• Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark [69.8473923357969]
  Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration.<n>We present Uni-MMMU, a comprehensive benchmark that unfolds the bidirectional synergy between generation and understanding across eight reasoning-centric domains.
  arXiv  Detail & Related papers  (2025-10-15T17:10:35Z)
• Contrastive Mutual Information Learning: Toward Robust Representations without Positive-Pair Augmentations [0.0]
  We introduce the contrastive Mutual Information Machine (cMIM), a probabilistic framework that extends the Mutual Information Machine (MIM) with a contrastive objective.<n>CMIM addresses this gap by imposing global discriminative structure while retaining MIM's generative fidelity.<n>We provide empirical evidence across vision and molecular benchmarks showing that cMIM outperforms MIM and InfoNCE on classification and regression tasks.
  arXiv  Detail & Related papers  (2025-09-25T20:03:24Z)
• UCD: Unlearning in LLMs via Contrastive Decoding [10.901118996654171]
  We propose an inference-time unlearning algorithm that uses contrastive decoding.<n>We evaluate our approach on two unlearning benchmarks, TOFU and MUSE.
  arXiv  Detail & Related papers  (2025-06-12T16:02:26Z)
• MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems [31.53306157650065]
  Multimodal retrieval-augmented generation (RAG) systems enhance large vision-language models by integrating cross-modal knowledge.<n>These knowledge databases may contain sensitive information that requires privacy protection.<n>MrM is the first black-box MIA framework targeted at multimodal RAG systems.
  arXiv  Detail & Related papers  (2025-06-09T03:48:50Z)
• USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation [24.90512145836643]
  We introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation.<n>We show that our approach significantly outperforms the current state-of-the-art (SOTA) approaches.
  arXiv  Detail & Related papers  (2024-12-12T12:20:27Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning [18.152453141040464]
  Unsupervised Few-Shot Learning seeks to bridge this divide by reducing reliance on annotated datasets during initial training phases. We first quantitatively assess the impacts of Masked Image Modeling (MIM) and Contrastive Learning (CL) on few-shot learning tasks. To address these trade-offs between generalization and discriminability in unsupervised pretraining, we introduce a novel paradigm named Masked Image Contrastive Modeling (MICM)
  arXiv  Detail & Related papers  (2024-08-23T21:32:53Z)
• Constructing Enhanced Mutual Information for Online Class-Incremental Learning [11.555090963348595]
  Online Class-Incremental continual Learning (OCIL) addresses the challenge of continuously learning from a single-channel data stream. Existing Mutual Information (MI)-based methods treat various knowledge components in isolation, ignoring the knowledge confusion across tasks. We propose an Enhanced Mutual Information (EMI) method based on knwoledge decoupling.
  arXiv  Detail & Related papers  (2024-07-26T06:16:11Z)
• On the Role of Discrete Tokenization in Visual Representation Learning [35.10829554701771]
  Masked image modeling (MIM) has gained popularity alongside contrastive learning methods. discrete tokens as the reconstruction target, but the theoretical underpinnings of this choice remain underexplored. We provide a comprehensive theoretical understanding on how discrete tokenization affects the model's generalization capabilities. We propose a novel metric named TCAS, which is specifically designed to assess the effectiveness of discrete tokens within the MIM framework.
  arXiv  Detail & Related papers  (2024-07-12T08:25:31Z)
• Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning [53.00683059396803]
  Mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images. We propose a decision-based MIM that utilizes reinforcement learning (RL) to automatically search for optimal image masking ratio and masking strategy. Our approach has a significant advantage over alternative self-supervised methods on the task of neuron segmentation.
  arXiv  Detail & Related papers  (2023-10-06T10:40:46Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning [128.19212716007794]
  We propose an effective framework called textbfMulti-textbfAgent textbfMasked textbfAttentive textbfContrastive textbfLearning (MA2CL) MA2CL encourages learning representation to be both temporal and agent-level predictive by reconstructing the masked agent observation in latent space. Our method significantly improves the performance and sample efficiency of different MARL algorithms and outperforms other methods in various vision-based and state-based scenarios.
  arXiv  Detail & Related papers  (2023-06-03T05:32:19Z)
• MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers [140.0479479231558]
  In this work, we aim to unify a variety of pre-training tasks into a multi-task pre-trained model, namely MASTER. MASTER utilizes a shared-encoder multi-decoder architecture that can construct a representation bottleneck to compress the abundant semantic information across tasks into dense vectors.
  arXiv  Detail & Related papers  (2022-12-15T13:57:07Z)
• Self-Supervised Learning via Maximum Entropy Coding [57.56570417545023]
  We propose Maximum Entropy Coding (MEC) as a principled objective that explicitly optimize on the structure of the representation. MEC learns a more generalizable representation than previous methods based on specific pretext tasks. It achieves state-of-the-art performance consistently on various downstream tasks, including not only ImageNet linear probe, but also semi-supervised classification, object detection, instance segmentation, and object tracking.
  arXiv  Detail & Related papers  (2022-10-20T17:58:30Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)
• Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing [73.29587731448345]
  We propose a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH) We learn informative representations that can preserve both intra- and inter-modal similarities. The proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.
  arXiv  Detail & Related papers  (2021-12-13T08:58:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.