Search Results for author: Junhao Zheng

Found 12 papers, 5 papers with code

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

1 code implementation26 Mar 2024 Junhao Zheng, Chenhao Lin, Jiahao Sun, Zhengyu Zhao, Qian Li, Chao Shen

Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks.

Adversarial Attack Autonomous Driving +1

Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings

no code implementations23 Feb 2024 Junlong Liu, Xichen Shang, Huawen Feng, Junhao Zheng, Qianli Ma

However, due to the token bias in pretrained language models, the models can not capture the fine-grained semantics in sentences, which leads to poor predictions.

Contrastive Learning Sentence +2

Conditional Logical Message Passing Transformer for Complex Query Answering

no code implementations20 Feb 2024 Chongzhi Zhang, Zhiping Peng, Junhao Zheng, Qianli Ma

In this paper, we propose Conditional Logical Message Passing Transformer (CLMPT), which considers the difference between constants and variables in the case of using pre-trained neural link predictors and performs message passing conditionally on the node type.

Complex Query Answering Logical Reasoning

Incremental Sequence Labeling: A Tale of Two Shifts

no code implementations16 Feb 2024 Shengjie Qiu, Junhao Zheng, Zhen Liu, Yicheng Luo, Qianli Ma

As for the E2O problem, we use knowledge distillation to maintain the model's discriminative ability for old entities.

Knowledge Distillation

Balancing the Causal Effects in Class-Incremental Learning

no code implementations15 Feb 2024 Junhao Zheng, Ruiyan Wang, Chongzhi Zhang, Huawen Feng, Qianli Ma

In this way, the model is encouraged to adapt to all classes with causal effects from both new and old data and thus alleviates the causal imbalance problem.

Class Incremental Learning Continual Named Entity Recognition +6

Concept-1K: A Novel Benchmark for Instance Incremental Learning

1 code implementation13 Feb 2024 Junhao Zheng, Shengjie Qiu, Qianli Ma

However, existing IL scenarios and datasets are unqualified for assessing forgetting in PLMs, giving an illusion that PLMs do not suffer from catastrophic forgetting.

Incremental Learning

Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer

no code implementations17 Jan 2024 Junhao Zheng, Qianli Ma, Zhen Liu, Binquan Wu, Huawen Feng

The discrepancy results in the model learning irrelevant information for old and pre-trained tasks, which leads to catastrophic forgetting and negative forward transfer.

Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models

1 code implementation13 Dec 2023 Junhao Zheng, Shengjie Qiu, Qianli Ma

Most assume that catastrophic forgetting is the biggest obstacle to achieving superior IL performance and propose various techniques to overcome this issue.

Class Incremental Learning Incremental Learning +7

Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference

1 code implementation19 Jun 2023 Junhao Zheng, Qianli Ma, Shengjie Qiu, Yue Wu, Peitian Ma, Junlong Liu, Huawen Feng, Xichen Shang, Haibin Chen

Intriguingly, the unified objective can be seen as the sum of the vanilla fine-tuning objective, which learns new knowledge from target data, and the causal objective, which preserves old knowledge from PLMs.

Attribute Causal Inference

Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition

1 code implementation8 Oct 2022 Junhao Zheng, Zhanxian Liang, Haibin Chen, Qianli Ma

Thanks to the causal inference, we identify that the forgetting is caused by the missing causal effect from the old data.

Causal Inference FG-1-PG-1 +4

Cannot find the paper you are looking for? You can Submit a new open access paper.