Qingbo Wu

Multiple resources scheduling for diverse workloads in heterogeneous datacenter

2015

Multiple resources allocation in large scale datacenter has been widely studied and used in recent years. However, the existing scheduling methods have some shortcomings in the heterogeneous environment, such as starving certain jobs, leaving some …

Towards an Efficient and Robust Adversarial Attack Against Neural Text Classifier

2022 · International Journal of Pattern Recognition and Artificial Intelligence

Adversarial attack is a serious threat to neural network-based natural language processing applications. Adversarial attack uses tiny well-crafted perturbations to mislead neural networks. While existing adversarial text attacks can achieve good attack effects, they still …

GFR: Generic feature representations for class incremental learning

2023 · Neurocomputing

Class incremental learning (CIL) aims to continuously learn new classes while maintaining discrimination for old classes with sequentially coming data. Due to the lack of old-class samples, existing CIL methods fail to learn discriminative representations …

CafeBoost: Causal Feature Boost to Eliminate Task-Induced Bias for Class Incremental Learning

2023

Continual learning requires a model to incrementally learn a sequence of tasks and aims to predict well on all the learned tasks so far, which notoriously suffers from the catastrophic forgetting problem. In this paper, …

IoU-CLIP: IoU-Aware Language-Image Model Tuning for Open Vocabulary Object Detection

2024

Open vocabulary object detection (OVD), which detects novel categories through detectors trained on base categories, has achieved remarkable advancement attributable to large-scale vision-language models, such as CLIP. The prior OVD works mainly focused on improving …