Author name cluster

Xiaokang Chen

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.

8 papers

2 author rows

IJCAI Conference 2024 Conference Paper

D3ETR: Decoder Distillation for Detection Transformer

Xiaokang Chen
Jiahui Chen
Yan Liu
Jiaxiang Tang
Gang Zeng

Although various knowledge distillation (KD) methods for CNN-based detectors have been proven effective in improving small students, build- ing baselines and recipes for DETR-based detec- tors remains a challenge. This paper concentrates on the transformer decoder of DETR-based detec- tors and explores KD methods suitable for them. However, the random order of the decoder outputs poses a challenge for knowledge distillation as it provides no direct correspondence between the pre- dictions of the teacher and the student. To this end, we propose MixMatcher that aligns the de- coder outputs of DETR-based teacher and student, by mixing two teacher-student matching strategies for combined advantages. The first strategy, Adap- tive Matching, applies bipartite matching to adap- tively match the outputs of the teacher and the stu- dent in each decoder layer. The second strategy, Fixed Matching, fixes the correspondence between the outputs of the teacher and the student with the same object queries as input, which alleviates in- stability of bipartite matching in Adaptive Match- ing. Using both strategies together produces bet- ter results than using either strategy alone. Based on MixMatcher, we devise Decoder Distillation for DEtection TRansformer (D3ETR), which dis- tills knowledge in decoder predictions and attention maps from the teacher to student. D3ETR shows superior performance on various DETR-based de- tectors with different backbones. For instance, D3ETR improves Conditional DETR-R50-C5 by 8. 3 mAP under 12 epochs training setting with Conditional DETR-R101-C5 serving as the teacher. The code will be released.

PDF Details DOI

ICLR Conference 2024 Conference Paper

The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models

Yan Liu 0002
Yu Liu
Xiaokang Chen
Pin-Yu Chen
Daoguang Zan
Min-Yen Kan
Tsung-Yi Ho

Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic results in application. Previous works on this problem mainly focused on using black-box methods such as probing to detect and quantify social biases in PLMs by observing model outputs. As a result, previous debiasing methods mainly finetune or even pre-train PLMs on newly constructed anti-stereotypical datasets, which are high-cost. In this work, we try to unveil the mystery of social bias inside language models by introducing the concept of {\sc Social Bias Neurons}. Specifically, we propose {\sc Integrated Gap Gradients (IG$^2$)} to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias. By formalizing undesirable behavior as a distributional property of language, we employ sentiment-bearing prompts to elicit classes of sensitive words (demographics) correlated with such sentiments. Our IG$^2$ thus attributes the uneven distribution for different demographics to specific Social Bias Neurons, which track the trail of unwanted behavior inside PLM units to achieve interoperability. Moreover, derived from our interpretable technique, {\sc Bias Neuron Suppression (BNS)} is further proposed to mitigate social biases. By studying BERT, RoBERTa, and their attributable differences from debiased FairBERTa, IG$^2$ allows us to locate and suppress identified neurons, and further mitigate undesired behaviors. As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost\footnote{This work contains examples that potentially implicate stereotypes, associations, and other harms that could be offensive to individuals in certain social groups.}.

Details

TMLR Journal 2023 Journal Article

CAE v2: Context Autoencoder with CLIP Latent Alignment

Xinyu Zhang
Jiahui Chen
Junkun Yuan
Qiang Chen
Jian Wang
Xiaodi Wang
Shumin Han
Xiaokang Chen

Masked image modeling (MIM) learns visual representations by predicting the masked patches on a pre-defined target. Inspired by MVP(Wei et al., 2022b) that displays impressive gains with CLIP, in this work, we also employ the semantically rich CLIP latent as target and further tap its potential by introducing a new MIM pipeline, CAE v2, to learn a high-quality encoder and facilitate model convergence on the pre-training task. CAE v2 is an improved variant of CAE (Chen et al., 2023), applying the CLIP latent on two pretraining tasks, i.e., visible latent alignment and masked latent alignment. Visible latent alignment directly mimics the visible latent representations from the encoder to the corresponding CLIP latent, which is beneficial for facilitating model convergence and improving the representative ability of the encoder. Masked latent alignment predicts the representations of masked patches within the feature space of CLIP latent as standard MIM task does, effectively aligning the representations computed from the encoder and the regressor into the same domain. We pretrain CAE v2 on ImageNet-1K images and evaluate on various downstream vision tasks, including image classification, semantic segmentation, object detection and instance segmentation. Experiments show that our CAE v2 achieves competitive performance and even outperforms the CLIP vision encoder, demonstrating the effectiveness of our method. Code is available at https://github.com/Atten4Vis/CAE.

PDF Details

NeurIPS Conference 2023 Conference Paper

Uncovering and Quantifying Social Biases in Code Generation

Yan Liu
Xiaokang Chen
Yan Gao
Zhe Su
Fengji Zhang
Daoguang Zan
Jian-Guang Lou
Pin-Yu Chen

With the popularity of automatic code generation tools, such as Copilot, the study of the potential hazards of these tools is gaining importance. In this work, we explore the social bias problem in pre-trained code generation models. We propose a new paradigm to construct code prompts and successfully uncover social biases in code generation models. To quantify the severity of social biases in generated code, we develop a dataset along with three metrics to evaluate the overall social bias and fine-grained unfairness across different demographics. Experimental results on three pre-trained code generation models (Codex, InCoder, and CodeGen) with varying sizes, reveal severe social biases. Moreover, we conduct analysis to provide useful insights for further choice of code generation models with low social bias.

PDF Details

TMLR Journal 2023 Journal Article

Understanding Self-Supervised Pretraining with Part-Aware Representation Learning

Jie Zhu
Jiyang Qi
Mingyu Ding
Xiaokang Chen
Ping Luo
Xinggang Wang
Wenyu Liu
Leye Wang

In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised methods learn part-aware representations. The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts. We explain that contrastive learning is a part-to-whole task: the projection layer hallucinates the whole object representation from the object part representation learned from the encoder, and that masked image modeling is a part-to-part task: the masked patches of the object are hallucinated from the visible patches. The explanation suggests that the self-supervised pretrained encoder leans toward understanding the object part. We empirically compare the off-the-shelf encoders pretrained with several representative methods on object-level recognition and part-level recognition. The results show that the fully-supervised model outperforms self-supervised models for object-level recognition, and most self-supervised contrastive learning and masked image modeling methods outperform the fully-supervised method for part-level recognition. It is observed that the combination of contrastive learning and masked image modeling further improves the performance.

PDF Details

NeurIPS Conference 2023 Conference Paper

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

Wenhai Wang
Zhe Chen
Xiaokang Chen
Jiannan Wu
Xizhou Zhu
Gang Zeng
Ping Luo
Tong Lu

Large language models (LLMs) have notably accelerated progress towards artificial general intelligence (AGI), with their impressive zero-shot capacity for user-tailored tasks, endowing them with immense potential across a range of applications. However, in the field of computer vision, despite the availability of numerous powerful vision foundation models (VFMs), they are still restricted to tasks in a pre-defined form, struggling to match the open-ended task capabilities of LLMs. In this work, we present an LLM-based framework for vision-centric tasks, termed VisionLLM. This framework provides a unified perspective for vision and language tasks by treating images as a foreign language and aligning vision-centric tasks with language tasks that can be flexibly defined and managed using language instructions. An LLM-based decoder can then make appropriate predictions based on these instructions for open-ended tasks. Extensive experiments show that the proposed VisionLLM can achieve different levels of task customization through language instructions, from fine-grained object-level to coarse-grained task-level customization, all with good results. It's noteworthy that, with a generalist LLM-based framework, our model can achieve over 60% mAP on COCO, on par with detection-specific models. We hope this model can set a new baseline for generalist vision and language models. The code shall be released.

PDF Details

NeurIPS Conference 2022 Conference Paper

Compressible-composable NeRF via Rank-residual Decomposition

Jiaxiang Tang
Xiaokang Chen
Jingbo Wang
Gang Zeng

Neural Radiance Field (NeRF) has emerged as a compelling method to represent 3D objects and scenes for photo-realistic rendering. However, its implicit representation causes difficulty in manipulating the models like the explicit mesh representation. Several recent advances in NeRF manipulation are usually restricted by a shared renderer network, or suffer from large model size. To circumvent the hurdle, in this paper, we present a neural field representation that enables efficient and convenient manipulation of models. To achieve this goal, we learn a hybrid tensor rank decomposition of the scene without neural networks. Motivated by the low-rank approximation property of the SVD algorithm, we propose a rank-residual learning strategy to encourage the preservation of primary information in lower ranks. The model size can then be dynamically adjusted by rank truncation to control the levels of detail, achieving near-optimal compression without extra optimization. Furthermore, different models can be arbitrarily transformed and composed into one scene by concatenating along the rank dimension. The growth of storage cost can also be mitigated by compressing the unimportant objects in the composed scene. We demonstrate that our method is able to achieve comparable rendering quality to state-of-the-art methods, while enabling extra capability of compression and composition. Code is available at https: //github. com/ashawkey/CCNeRF.

PDF Details

AAAI Conference 2022 Conference Paper

Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective

Jiaxiang Tang
Xiaokang Chen
Jingbo Wang
Gang Zeng

We revisit Semantic Scene Completion (SSC), a useful task to predict the semantic and occupancy representation of 3D scenes, in this paper. A number of methods for this task are always based on voxelized scene representations for keeping local scene structure. However, due to the existence of visible empty voxels, these methods always suffer from heavy computation redundancy when the network goes deeper, and thus limit the completion quality. To address this dilemma, we propose our novel point-voxel aggregation network for this task. Firstly, we transfer the voxelized scenes to point clouds by removing these visible empty voxels and adopt a deep point stream to capture semantic information from the scene efficiently. Meanwhile, a light-weight voxel stream containing only two 3D convolution layers preserves local structures of the voxelized scenes. Furthermore, we design an anisotropic voxel aggregation operator to fuse the structure details from the voxel stream into the point stream, and a semantic-aware propagation module to enhance the up-sampling process in the point stream by semantic labels. We demonstrate that our model surpasses state-of-the-arts on two benchmarks by a large margin, with only depth images as the input.

PDF Details