UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog

• URL: http://arxiv.org/abs/2205.00423v2
• Date: Tue, 3 May 2022 09:25:00 GMT
• Title: UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
• Abstract summary: We propose a contrastive learning-based framework UTC to unify and facilitate both discriminative and generative tasks in visual dialog with a single model. We evaluate our proposed UTC on the VisDial v1.0 dataset, where our method outperforms the state-of-the-art on both discriminative and generative tasks.
• Score: 30.864390060624213
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual Dialog aims to answer multi-round, interactive questions based on the dialog history and image content. Existing methods either consider answer ranking and generating individually or only weakly capture the relation across the two tasks implicitly by two separate models. The research on a universal framework that jointly learns to rank and generate answers in a single model is seldom explored. In this paper, we propose a contrastive learning-based framework UTC to unify and facilitate both discriminative and generative tasks in visual dialog with a single model. Specifically, considering the inherent limitation of the previous learning paradigm, we devise two inter-task contrastive losses i.e., context contrastive loss and answer contrastive loss to make the discriminative and generative tasks mutually reinforce each other. These two complementary contrastive losses exploit dialog context and target answer as anchor points to provide representation learning signals from different perspectives. We evaluate our proposed UTC on the VisDial v1.0 dataset, where our method outperforms the state-of-the-art on both discriminative and generative tasks and surpasses previous state-of-the-art generative methods by more than 2 absolute points on Recall@1.

Related papers

• Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System [90.64481646805855]
  unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model.<n>We investigate their relationship at the representation, task, and system levels in a controlled, structurally native setting.<n>We show that the value of UMMs extends beyond a unified interface: appropriate specialization, shared task knowledge, and end-to-end optimization can turn coexistence into synergy.
  arXiv  Detail & Related papers  (2026-09-01T17:59:59Z)
• Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking [154.2388970262703]
  Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework.<n>We introduce the interleaved Analyzing-Drafting problem-solving loop (AD-Loop), a new think paradigm that alternates between analytic and drafting operations.<n>By interleaving textual thoughts with visual thoughts, AD-Loop enables models to iteratively refine both comprehension and outputs, fostering genuine synergy.
  arXiv  Detail & Related papers  (2026-02-24T23:26:09Z)
• UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations [71.79210031338464]
  We show how to unify dense retrieval and response generation for large language models in conversation.<n>We conduct joint fine-tuning with different objectives and design two mechanisms to reduce the inconsistency risks.<n>The evaluations on five conversational search datasets demonstrate that our unified model can mutually improve both tasks and outperform the existing baselines.
  arXiv  Detail & Related papers  (2025-07-09T17:02:40Z)
• Aligning and Prompting Everything All at Once for Universal Visual Perception [79.96124061108728]
  APE is a universal visual perception model for aligning and prompting everything all at once in an image to perform diverse tasks. APE advances the convergence of detection and grounding by reformulating language-guided grounding as open-vocabulary detection. Experiments on over 160 datasets demonstrate that APE outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-04T18:59:50Z)
• SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding [68.94808536012371]
  We propose a tree-structured pre-trained conversation model, which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora. Our method can achieve new state-of-the-art results on the DialoGLUE benchmark consisting of seven datasets and four popular dialog understanding tasks.
  arXiv  Detail & Related papers  (2022-09-14T13:42:50Z)
• Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation [59.01297461453444]
  We propose a hierarchical contrastive learning mechanism, which can unify hybrid granularities semantic meaning in the input text. Experiments demonstrate that our model outperforms competitive baselines on paraphrasing, dialogue generation, and storytelling tasks.
  arXiv  Detail & Related papers  (2022-05-26T13:26:03Z)
• Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue [22.103162555263143]
  We introduce contrastive learning and multi-task learning to jointly model the problem. Our proposed model achieves state-of-the-art performance on several public datasets.
  arXiv  Detail & Related papers  (2022-03-22T10:13:27Z)
• Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue [18.668723854662584]
  This paper applies contrastive learning to the problem by using the supervised contrastive loss. We develop a new method for supervised contrastive learning, referred to as two-level supervised contrastive learning.
  arXiv  Detail & Related papers  (2022-03-01T23:43:36Z)
• Generalizable and Explainable Dialogue Generation via Explicit Action Learning [33.688270031454095]
  Conditioned response generation serves as an effective approach to optimize task completion and language quality. latent action learning is introduced to map each utterance to a latent representation. This approach is prone to over-dependence on the training data, and the generalization capability is thus restricted. Our proposed approach outperforms latent action baselines on MultiWOZ, a benchmark multi-domain dataset.
  arXiv  Detail & Related papers  (2020-10-08T04:37:22Z)
• Generating Dialogue Responses from a Semantic Latent Space [75.18449428414736]
  We propose an alternative to the end-to-end classification on vocabulary. We learn the pair relationship between the prompts and responses as a regression task on a latent space. Human evaluation showed that learning the task on a continuous space can generate responses that are both relevant and informative.
  arXiv  Detail & Related papers  (2020-10-04T19:06:16Z)
• Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues [88.73739515457116]
  We introduce four self-supervised tasks including next session prediction, utterance restoration, incoherence detection and consistency discrimination. We jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner. Experiment results indicate that the proposed auxiliary self-supervised tasks bring significant improvement for multi-turn response selection.
  arXiv  Detail & Related papers  (2020-09-14T08:44:46Z)
• DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification [77.59549450705384]
  In dialog system, dialog act recognition and sentiment classification are two correlative tasks. Most of the existing systems either treat them as separate tasks or just jointly model the two tasks. We propose a Deep Co-Interactive Relation Network (DCR-Net) to explicitly consider the cross-impact and model the interaction between the two tasks.
  arXiv  Detail & Related papers  (2020-08-16T14:13:32Z)

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.