13 citations · 18 across the 8 of their papers we have counts for
8 papers
Knowledge Distillation from Single to Multi Labels: an Empirical Study
Youcai Zhang, Yuzhuo Qin, Hengwei Liu +3
Knowledge distillation (KD) has been extensively studied in single-label image classification. However, its efficacy for multi-label classification remains relatively unexplored. I…
Continuous Decomposition of Granularity for Neural Paraphrase Generation
Xiaodong Gu, Zhaowei Zhang, Sang-Woo Lee +2
While Transformers have had significant success in paragraph generation, they treat sentences as linear sequences of tokens and often neglect their hierarchical information. Prior…
Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networks
Qingrong Cheng, Keyu Wen, Xiaodong Gu
Text-to-image synthesis aims to generate a photo-realistic and semantic consistent image from a specific text description. The images synthesized by off-the-shelf models usually co…
A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
Zhenshan Tan, Cheng Chen, Keyu Wen +2
Co-saliency detection (CoSOD) aims at discovering the repetitive salient objects from multiple images. Two primary challenges are group semantics extraction and noise object suppre…
Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval
Keyu Wen, Zhenshan Tan, Qingrong Cheng +2
Recently, the cross-modal pre-training task has been a hotspot because of its wide application in various down-streaming researches including retrieval, captioning, question answer…
UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
Cheng Chen, Yudong Zhu, Zhenshan Tan +4
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 indivi…
Response Generation with Context-Aware Prompt Learning
Xiaodong Gu, Kang Min Yoo, Sang-Woo Lee
Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce…
DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances
Xiaodong Gu, Kang Min Yoo, Jung-Woo Ha
Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear seque…