Lingxi Xie

In this study, we introduce EinsPT, an efficient instance-aware pre-training paradigm designed to reduce the transfer gap between vision foundation models and downstream instance-level tasks. Unlike conventional image-level pre-training that relies solely on unlabeled images, EinsPT leverages both image reconstruction and instance annotations to learn representations that are spatially coherent and instance discriminative. To achieve this efficiently, we propose a proxy-foundation architecture that decouples high-resolution and low-resolution learning: the foundation model processes masked low-resolution images for global semantics, while a lightweight proxy model operates on complete high-resolution images to preserve fine-grained details. The two branches are jointly optimized through reconstruction and instance-level prediction losses on fused features. Extensive experiments demonstrate that EinsPT consistently enhances recognition accuracy across various downstream tasks with substantially reduced computational cost, while qualitative results further reveal improved instance perception and completeness in visual representations. Code is available at github.com/feufhd/EinsPT.

In this study, we establish a benchmark and a baseline approach for Multimodal referring and grounding with Chain-of-Questions (MCQ), opening up a promising direction for ‘logical’ multimodal dialogues. The newly collected dataset, named CB-300K, spans challenges including probing dialogues with spatial relationship among multiple objects, consistent reasoning, and complex question chains. The baseline approach, termed ChatterBox, involves a modularized design and a referent feedback mechanism to ensure logical coherence in continuous referring and grounding tasks. This design reduces the risk of referential confusion, simplifies the training process, and presents validity in retaining the language model’s generation ability. Experiments show that ChatterBox demonstrates superiority in MCQ both quantitatively and qualitatively, paving a new path towards multimodal dialogue scenarios with logical interactions.

Object recognition using single-point supervision has attracted increasing attention recently. However, the performance gap compared with fully-supervised algorithms remains large. Previous works generated class-agnostic \textbf{\textit{proposals in an image}} offline and then treated mixed candidates as a single bag, putting a huge burden on multiple instance learning (MIL). In this paper, we introduce Point-to-Box Network (P2BNet), which constructs balanced \textbf{\textit{instance-level proposal bags}} by generating proposals in an anchor-like way and refining the proposals in a coarse-to-fine paradigm. Through further research, we find that the bag of proposals, either at the image level or the instance level, is established on discrete box sampling. This leads the pseudo box estimation into a sub-optimal solution, resulting in the truncation of object boundaries or the excessive inclusion of background. Hence, we conduct a series exploration of discrete-to-continuous optimization, yielding P2BNet++ and Point-to-Mask Network (P2MNet). P2BNet++ conducts an approximately continuous proposal sampling strategy by better utilizing spatial clues. P2MNet further introduces low-level image information to assist in pixel prediction, and a boundary self-prediction is designed to relieve the limitation of the estimated boxes. Benefiting from the continuous object-aware \textbf{\textit{pixel-level perception}}, P2MNet can generate more precise bounding boxes and generalize to segmentation tasks. Our method largely surpasses the previous methods in terms of the mean average precision on COCO, VOC, SBD, and Cityscapes, demonstrating great potential to bridge the performance gap compared with fully supervised tasks.

Zero-shot learning (ZSL) focuses on recognizing unseen categories by aligning visual features with semantic information. Recent advancements have shown that aligning each attribute with its corresponding visual region significantly improves zero-shot learning performance. However, the crude semantic proxies used in these methods fail to capture the varied appearances of each attribute, and are also easily confused by the presence of semantically redundant backgrounds, leading to suboptimal alignment. To combat these issues, we introduce a novel Alignment-Enhanced Network (AENet), designed to denoise the visual features and dynamically perceive semantic information, thus enhancing visual-semantic alignment. Our approach comprises two key innovations. (1) A visual denoising encoder, employing a class-agnostic mask to filter out semantically redundant visual information, thus producing refined visual features adaptable to unseen classes. (2) A dynamic semantic generator that crafts content-aware semantic proxies adaptively, steered by visual features, enabling AENet to discriminate fine-grained variations in visual contents. Additionally, we integrate a cross-fusion module to ensure comprehensive interaction between the denoised visual features and the generated dynamic semantic proxies, further facilitating visual-semantic alignment. Through extensive experiments across three datasets, the proposed method demonstrates that it narrows down the visual-semantic gap and sets a new benchmark in this setting.

Reconstructing and rendering 3D objects from highly sparse views is of critical importance for promoting applications of 3D vision techniques and improving user experience. However, images from sparse views only contain very limited 3D information, leading to two significant challenges: 1) Difficulty in building multi-view consistency as images for matching are too few; 2) Partially omitted or highly compressed object information as view coverage is insufficient. To tackle these challenges, we propose GaussianObject, a framework to represent and render the 3D object with Gaussian splatting that achieves high rendering quality with only 4 input images. We first introduce techniques of visual hull and floater elimination, which explicitly inject structure priors into the initial optimization process to help build multi-view consistency, yielding a coarse 3D Gaussian representation. Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined. We design a self-generating strategy to obtain image pairs for training the repair model. We further design a COLMAP-free variant, where pre-given accurate camera poses are not required, which achieves competitive quality and facilitates wider applications. GaussianObject is evaluated on several challenging datasets, including MipNeRF360, OmniObject3D, OpenIllumination, and our-collected unposed images, achieving superior performance from only four views and significantly outperforming previous SOTA methods.

Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer. Instead, recent advances can achieve superior performance than full-tuning the whole pre-trained parameters by updating far fewer parameters, enabling edge devices and downstream applications to reuse the increasingly large foundation models deployed on the cloud. With the aim of helping researchers get the full picture and future directions of visual tuning, this survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of existing work and models. Specifically, it provides a detailed background of visual tuning and categorizes recent visual tuning techniques into five groups: fine-tuning, prompt tuning, adapter tuning, parameter tuning, and remapping tuning. Meanwhile, it offers some exciting research directions for prospective pre-training and various interactions in visual tuning.