arXiv subjects

Zhibin Quan

Publications and source records attributed to Zhibin Quan.

4 recordsLinked to original sources

arXiv2025

Vision Remember: Recovering Visual Information in Efficient LVLM with Vision Feature Resampling

The computational expense of redundant vision tokens in Large Vision-Language Models (LVLMs) has led many existing methods to compress them via a vision projector. However, this compression may lose visual information that is crucial for tasks relying on fine-grained spatial relationships, such as OCR and Chart&Table Understanding. In this paper, we propose to resample original vision features across the LLM decoder layers to recover visual information and attain efficiency. Following this principle, we introduce Vision Remember, which includes two key modules: (1) Token-Feature Cross-Attention Layer and (2) Token Bidirectional Self-Attention Layer. In the Token bidirectional attention, we employ self-attention mechanism to maintain the bidirectional interaction between vision tokens and the text-guided token. In the Token-Feature interaction attention, we introduce local cross-attention to resample the visual feature and utilize the multi-level fusion to enrich the visual representation. We conduct comprehensive experiments on multiple visual understanding benchmarks and the results with the LLaVA-NeXT baseline show that Vision Remember outperforms TokenPacker by +2.7 and FastV by +5.7 across nearly all the settings. Compared with previous vision feature re-fusion methods, our approach also surpasses DeepStack by +3.9 and SVA Aggregator by +3.4 on the same baseline. The experimental results validate the generalization capability of the proposed method when combined with various efficient vision projectors and LVLMs.

cs.CV↗

arXiv2021

Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association

This paper presents a new method to solve keypoint detection and instance association by using Transformer. For bottom-up multi-person pose estimation models, they need to detect keypoints and learn associative information between keypoints. We argue that these problems can be entirely solved by Transformer. Specifically, the self-attention in Transformer measures dependencies between any pair of locations, which can provide association information for keypoints grouping. However, the naive attention patterns are still not subjectively controlled, so there is no guarantee that the keypoints will always attend to the instances to which they belong. To address it we propose a novel approach of supervising self-attention for multi-person keypoint detection and instance association. By using instance masks to supervise self-attention to be instance-aware, we can assign the detected keypoints to their corresponding instances based on the pairwise attention scores, without using pre-defined offset vector fields or embedding like CNN-based bottom-up models. An additional benefit of our method is that the instance segmentation results of any number of people can be directly obtained from the supervised attention matrix, thereby simplifying the pixel assignment pipeline. The experiments on the COCO multi-person keypoint detection challenge and person instance segmentation task demonstrate the effectiveness and simplicity of the proposed method and show a promising way to control self-attention behavior for specific purposes.

cs.CV↗

arXiv2021

TransPose: Keypoint Localization via Transformer

While CNN-based models have made remarkable progress on human pose estimation, what spatial dependencies they capture to localize keypoints remains unclear. In this work, we propose a model called \textbf{TransPose}, which introduces Transformer for human pose estimation. The attention layers built in Transformer enable our model to capture long-range relationships efficiently and also can reveal what dependencies the predicted keypoints rely on. To predict keypoint heatmaps, the last attention layer acts as an aggregator, which collects contributions from image clues and forms maximum positions of keypoints. Such a heatmap-based localization approach via Transformer conforms to the principle of Activation Maximization~\cite{erhan2009visualizing}. And the revealed dependencies are image-specific and fine-grained, which also can provide evidence of how the model handles special cases, e.g., occlusion. The experiments show that TransPose achieves 75.8 AP and 75.0 AP on COCO validation and test-dev sets, while being more lightweight and faster than mainstream CNN architectures. The TransPose model also transfers very well on MPII benchmark, achieving superior performance on the test set when fine-tuned with small training costs. Code and pre-trained models are publicly available\footnote{\url{https://github.com/yangsenius/TransPose}}.

cs.CV↗

arXiv2021

SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud

LiDAR-based 3D object detection pushes forward an immense influence on autonomous vehicles. Due to the limitation of the intrinsic properties of LiDAR, fewer points are collected at the objects farther away from the sensor. This imbalanced density of point clouds degrades the detection accuracy but is generally neglected by previous works. To address the challenge, we propose a novel two-stage 3D object detection framework, named SIENet. Specifically, we design the Spatial Information Enhancement (SIE) module to predict the spatial shapes of the foreground points within proposals, and extract the structure information to learn the representative features for further box refinement. The predicted spatial shapes are complete and dense point sets, thus the extracted structure information contains more semantic representation. Besides, we design the Hybrid-Paradigm Region Proposal Network (HP-RPN) which includes multiple branches to learn discriminate features and generate accurate proposals for the SIE module. Extensive experiments on the KITTI 3D object detection benchmark show that our elaborately designed SIENet outperforms the state-of-the-art methods by a large margin.

cs.CV↗