Search Results for author:
Found 25 papers, 12 papers with code
Towards Aligned Data Removal via Twin Machine Unlearning
Nonetheless, the authentic objective of machine unlearning is to align the unlearned model with the gold model, i. e., achieving the same classification accuracy as the gold model.
Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate
MLLMs often generate outputs that are inconsistent with the visual content, a challenge known as hallucination.
Efficient LLM-Jailbreaking by Introducing Visual Modality
Finally, we convert the embJS into text space to facilitate the jailbreaking of the target LLM.
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
Specifically, our PUD has a progressive model purification scheme to jointly erase backdoors and enhance the model's adversarial robustness.
Jailbreaking Attack against Multimodal Large Language Model
This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries.
Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Ones
However, BiRNN is intrinsically offline because it uses backward recurrent modules to propagate from the last to current frames, which causes high latency and large memory consumption.
Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis
Obviously, a fine-grained part-level semantic layout will benefit object details generation, and it can be roughly inferred from an object's shape.
Towards Simple and Accurate Human Pose Estimation with Stair Network
In this paper, we focus on tackling the precise keypoint coordinates regression task.
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks
Deep neural networks (DNNs) are known to be vulnerable to both backdoor attacks as well as adversarial attacks.
Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters
In this paper, we defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset.
Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction
Specifically, the proposed unlimited neighborhood interaction module generates the fused-features of all agents involved in an interaction simultaneously, which is adaptive to any number of agents and any range of interaction area.
SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians.
Structure First Detail Next: Image Inpainting with Pyramid Generator
Recent deep generative models have achieved promising performance in image inpainting.
Video Imprint
In the proposed framework, a dedicated feature alignment module is incorporated for redundancy removal across frames to produce the tensor representation, i. e., the video imprint.
Adversarial Attack and Defense in Deep Ranking
In this paper, we propose two attacks against deep ranking systems, i. e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations.
Image Inpainting with Edge-guided Learnable Bidirectional Attention Maps
In this paper, we present an edge-guided learnable bidirectional attention map (Edge-LBAM) for improving image inpainting of irregular holes with several distinct merits.
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Meanwhile, we use a sparse directed temporal graph to model the motion tendency, thus to facilitate the prediction based on the observed direction.
Practical Relative Order Attack in Deep Ranking
In this paper, we formulate a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order among a selected set of candidates according to an attacker-specified permutation, with limited interference to other unrelated candidates.
Practical Order Attack in Deep Ranking
The objective of this paper is to formalize and practically implement a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order of a selected set of candidates according to a permutation vector predefined by the attacker, with only limited interference to other unrelated candidates.
Adversarial Ranking Attack and Defense
In this paper, we propose two attacks against deep ranking systems, i. e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations.
Ladder Loss for Coherent Visual-Semantic Embedding
For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way -- relevant or irrelevant, and all "irrelevant" candidates are uniformly pushed away from the query by an equal margin in the embedding space, regardless of their various proximity to the query.
Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs).
Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding
We address the problem of dense visual-semantic embedding that maps not only full sentences and whole images but also phrases within sentences and salient regions within images into a multimodal embedding space.
Ordinal Regression With Multiple Output CNN for Age Estimation
To address the non-stationary property of aging patterns, age estimation can be cast as an ordinal regression problem.
Semi-supervised Relational Topic Model for Weakly Annotated Image Recognition in Social Media
In such way, we can efficiently leverage the loosely related tags, and build an intermediate level representation for a collection of weakly annotated images.
