Author name cluster

Feifei Zhang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

Duplex Rewards Optimization for Test-Time Composed Image Retrieval

Haoliang Zhou
Feifei Zhang
Changsheng Xu

Composed Image Retrieval (CIR) combines the reference image with text to retrieve the intended target image. Recently, zero-shot CIR has gained significant attention by eliminating the need for labeled triplets required in supervised CIR. However, it inevitably demands additional training corpus, storage, and computational resources, limiting its applicability in real-world scenarios. Inspired by advancements in Test-Time Adaptation (TTA), we propose a Test-Time CIR setting named TT-CIR, which aims to efficiently adapt models to unlabeled test samples while reducing resource consumption. Within the TT-CIR setting, we identify that naively introducing existing TTA methods (e.g., reward-based) into CIR faces two vital challenges: 1) Modification-restricted reward pool, which limits the exploration of semantically relevant candidate rewards; 2) Conservative knowledge feedback, which inhibits the adaptability of rewards to the current data distribution. To address these challenges, we propose a test-time reinforcement learning framework that integrates a Counterfactual-guided Multinomial Sampling (CMS) strategy and a Duplex Rewards Modeling (DRM) module. The CMS explores a candidate reward pool that is visually similar and semantically relevant to the given query, while the DRM generates stable and adaptive duplex rewards to guide model adaptation. Extensive experiments demonstrate the superiority and adaptability of our method over existing approaches.

PDF Details DOI

AAAI Conference 2026 Conference Paper

OAD-Promoter: Enhancing Zero-Shot VQA Using Large Language Models with Object Attribute Description

Quanxing Xu
Ling Zhou
Feifei Zhang
Rubing Huang
Jinyu Tian

Large Language Models (LLMs) have become a crucial tool in Visual Question Answering (VQA) for handling knowledge-intensive questions in few-shot or zero-shot scenarios. However, their reliance on massive training datasets often causes them to inherit language biases during the acquisition of knowledge. This limitation imposes two key constraints on existing methods: (1) LLM predictions become less reliable due to bias exploitation, and (2) despite strong knowledge reasoning capabilities, LLMs still struggle with out-of-distribution (OOD) generalization. To address these issues, we propose Object Attribute Description Promoter (OAD-Promoter), a novel approach for enhancing LLM-based VQA by mitigating language bias and improving domain-shift robustness. OAD-Promoter comprises three components: the Object-concentrated Example Generation (OEG) module, the Memory Knowledge Assistance (MKA) module, and the OAD Prompt. The OEG module generates global captions and object-concentrated samples, jointly enhancing visual information input to the LLM and mitigating bias through complementary global and regional visual cues. The MKA module assists the LLM in handling OOD samples by retrieving relevant knowledge from stored examples to support questions from unseen domains. Finally, the OAD Prompt integrates the outputs of the preceding modules to optimize LLM inference. Experiments demonstrate that OAD-Promoter significantly improves the performance of LLM-based VQA methods in few-shot or zero-shot settings, achieving new state-of-the-art results.

PDF Details DOI

AAAI Conference 2025 Conference Paper

When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach

Feifei Zhang
Zhaoyi Zhang
Xi Zhang
Changsheng Xu

Visual Question Answering (VQA) is a multifaceted task that integrates computer vision and natural language processing to produce textual answers from images and questions. Existing VQA benchmarks predominantly adhere to a closed-set paradigm, limiting their ability to address arbitrary, unseen answers, and thus falling short in real-world scenarios. To address this limitation, we introduce the Open-Vocabulary Visual Question Answering (OVVQA) benchmark, specifically designed to evaluate models under open-world conditions by assessing their performance on both base classes (seen, common answers) and novel classes (unseen, rare answers). In conjunction with this benchmark, we propose a model-agnostic Causal Adapter to combat the inherent bias found in current VQA tasks. Our approach leverages front-door adjustment to enhance causal reasoning, significantly improving model performance on novel categories while maintaining accuracy on base classes. Additionally, we introduce an adaptive transfer loss to facilitate the transfer of more knowledge from the pretrained model to our OVVQA task. Extensive experiments across multiple datasets validate the superiority of our method over existing state-of-the-art approaches, demonstrating its robust generalization and adaptability in open-world VQA scenarios.

PDF Details DOI

YNICL Journal 2018 Journal Article

Altered white matter microarchitecture in amyotrophic lateral sclerosis: A voxel-based meta-analysis of diffusion tensor imaging

Feifei Zhang
Guangxiang Chen
Manxi He
Jing Dai
Huifang Shang
Qiyong Gong
Zhiyun Jia

Background: The results of recent diffusion tensor imaging (DTI) studies on amyotrophic lateral sclerosis (ALS) are inconclusive and controversial. We performed a voxel-based meta-analysis to identify a statistical consensus among published DTI studies of altered white matter (WM) microarchitecture in ALS. Methods: A systematic search was conducted for relevant studies that used voxel-wise analyses of WM microarchitecture in patients with ALS. Anisotropic effect size-signed differential mapping (AES-SDM) was applied to analyze fractional anisotropy (FA) differences between ALS patients and healthy controls. Meta-regression analysis was used to explore the effects of clinical characteristics on WM integrity in patients with ALS. Results: A total of 14 studies with 16 datasets that included 396 patients and 360 healthy controls were identified. The pooled meta-analysis revealed that patients with ALS exhibited significant FA reductions in two clusters relative to healthy controls. The largest cluster exhibited a peak coordinate in the left corona radiata, extending to the body and splenium of the corpus callosum, left superior longitudinal fasciculus, posterior limb of the internal capsule, right corona radiata, and bilateral cingulate gyrus. The other cluster exhibited decreased FA in the right corticospinal tract that extended to the right cerebral peduncle. The Amyotrophic Lateral Sclerosis Functional Rating Scale-Revised (ALSFRS-R) score was positively correlated with the FA reduction in the left corona radiata. Mean age and illness duration were not linearly correlated with the FA reductions. Conclusions: This study provides a thorough profile of WM microarchitecture alterations in patients with ALS and further evidence that the neuronal degeneration is not limited to the corticospinal tract but also includes extra-motor areas, which supports the view that ALS is a multisystem degenerative disorder that involves the white matter.

Details DOI