Bin Li

Dongshuo Yin, Leiyi Hu, Bin Li et al.

Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art fails to exceed the upper limit of full fine-tuning on challenging tasks like object detection and segmentation. To find a competitive alternative to full fine-tuning, we propose the Multi-cognitive Visual Adapter (Mona) tuning, a novel adapter-based tuning method. First, we introduce multiple vision-friendly filters into the adapter to enhance its ability to process visual signals, while previous methods mainly rely on language-friendly linear filters. Second, we add the scaled normalization layer in the adapter to regulate the distribution of input features for visual filters. To fully demonstrate the practicality and generality of Mona, we conduct experiments on multiple representative visual tasks, including instance segmentation on COCO, semantic segmentation on ADE20K, object detection on Pascal VOC, oriented object detection on DOTA/STAR, and image classification on three common datasets. Exciting results illustrate that Mona surpasses full fine-tuning on all these tasks, and is the only delta-tuning method outperforming full fine-tuning on the above various tasks. For example, Mona achieves 1% performance gain on the COCO dataset compared to full fine-tuning. Comprehensive results suggest that Mona-tuning is more suitable for retaining and utilizing the capabilities of pre-trained models than full fine-tuning. The code will be released at https://github.com/Leiyi-Hu/mona.

Fan Shi, Bin Li, Xiangyang Xue

Human cognition has compositionality. We understand a scene by decomposing the scene into different concepts (e.g., shape and position of an object) and learning the respective laws of these concepts, which may be either natural (e.g., laws of motion) or man-made (e.g., laws of a game). The automatic parsing of these laws indicates the model's ability to understand the scene, which makes law parsing play a central role in many visual tasks. This paper proposes a deep latent variable model for Compositional LAw Parsing (CLAP), which achieves the human-like compositionality ability through an encoding-decoding architecture to represent concepts in the scene as latent variables. CLAP employs concept-specific latent random functions instantiated with Neural Processes to capture the law of concepts. Our experimental results demonstrate that CLAP outperforms the baseline methods in multiple visual tasks such as intuitive physics, abstract visual reasoning, and scene representation. The law manipulation experiments illustrate CLAP's interpretability by modifying specific latent random functions on samples. For example, CLAP learns the laws of position-changing and appearance constancy from the moving balls in a scene, making it possible to exchange laws between samples or compose existing laws into novel laws.

Jiahao Li, Bin Li, Yan Lu

The emerging conditional coding-based neural video codec (NVC) shows superiority over commonly-used residual coding-based codec and the latest NVC already claims to outperform the best traditional codec. However, there still exist critical problems blocking the practicality of NVC. In this paper, we propose a powerful conditional coding-based NVC that solves two critical problems via feature modulation. The first is how to support a wide quality range in a single model. Previous NVC with this capability only supports about 3.8 dB PSNR range on average. To tackle this limitation, we modulate the latent feature of the current frame via the learnable quantization scaler. During the training, we specially design the uniform quantization parameter sampling mechanism to improve the harmonization of encoding and quantization. This results in a better learning of the quantization scaler and helps our NVC support about 11.4 dB PSNR range. The second is how to make NVC still work under a long prediction chain. We expose that the previous SOTA NVC has an obvious quality degradation problem when using a large intra-period setting. To this end, we propose modulating the temporal feature with a periodically refreshing mechanism to boost the quality. %Besides solving the above two problems, we also design a single model that can support both RGB and YUV colorspaces. Notably, under single intra-frame setting, our codec can achieve 29.7\% bitrate saving over previous SOTA NVC with 16\% MACs reduction. Our codec serves as a notable landmark in the journey of NVC evolution. The codes are at https://github.com/microsoft/DCVC.

Wei Zhang, Jiaxi Cao, Xiang Wang et al.

In recent years, head-mounted near-eye display devices have become the key hardware foundation for virtual reality and augmented reality. Thus head-mounted gaze tracking technology has received attention as an essential part of human-computer interaction. However, unavoidable slippage of head-mounted devices (HMD) often results higher gaze tracking errors and hinders the practical usage of HMD. To tackle this problem, we propose a slippage-robust gaze tracking for near-eye display method based on the aspheric eyeball model and accurately compute the eyeball optical axis and rotation center. We tested several methods on datasets with slippage and the experimental results show that the proposed method significantly outperforms the previous method (almost double the suboptimal method).

Chenfan Qu, Yiwu Zhong, Bin Li et al.

Images manipulated using image editing tools can mislead viewers and pose significant risks to social security. However, accurately localizing the manipulated regions within an image remains a challenging problem. One of the main barriers in this area is the high cost of data acquisition and the severe lack of high-quality annotated datasets. To address this challenge, we introduce novel methods that mitigate data scarcity by leveraging readily available web data. We utilize a large collection of manually forged images from the web, as well as automatically generated annotations derived from a simpler auxiliary task, constrained image manipulation localization. Specifically, we introduce a new paradigm CAAAv2, which automatically and accurately annotates manipulated regions at the pixel level. To further improve annotation quality, we propose a novel metric, QES, which filters out unreliable annotations. Through CAAA v2 and QES, we construct MIMLv2, a large-scale, diverse, and high-quality dataset containing 246,212 manually forged images with pixel-level mask annotations. This is over 120x larger than existing handcrafted datasets like IMD20. Additionally, we introduce Object Jitter, a technique that further enhances model training by generating high-quality manipulation artifacts. Building on these advances, we develop a new model, Web-IML, designed to effectively leverage web-scale supervision for the image manipulation localization task. Extensive experiments demonstrate that our approach substantially alleviates the data scarcity problem and significantly improves the performance of various models on multiple real-world forgery benchmarks. With the proposed web supervision, Web-IML achieves a striking performance gain of 31% and surpasses previous SOTA TruFor by 24.1 average IoU points. The dataset and code will be made publicly available at https://github.com/qcf-568/MIML.

Haiyang Yu, Xiaocong Wang, Bin Li et al.

Scene text recognition has been studied for decades due to its broad applications. However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text Recognition (CTR). Particularly, the characteristic of large categories poses challenges in dealing with zero-shot and few-shot Chinese characters. In this paper, inspired by the way humans recognize Chinese texts, we propose a two-stage framework for CTR. Firstly, we pre-train a CLIP-like model through aligning printed character images and Ideographic Description Sequences (IDS). This pre-training stage simulates humans recognizing Chinese characters and obtains the canonical representation of each character. Subsequently, the learned representations are employed to supervise the CTR model, such that traditional single-character recognition can be improved to text-line recognition through image-IDS matching. To evaluate the effectiveness of the proposed method, we conduct extensive experiments on both Chinese character recognition (CCR) and CTR. The experimental results demonstrate that the proposed method performs best in CCR and outperforms previous methods in most scenarios of the CTR benchmark. It is worth noting that the proposed method can recognize zero-shot Chinese characters in text images without fine-tuning, whereas previous methods require fine-tuning when new classes appear. The code is available at https://github.com/FudanVI/FudanOCR/tree/main/image-ids-CTR.

Mu Hu, Shuling Wang, Bin Li et al.

Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities plays an important role in achieving good performance. This paper proposes a two-branch backbone that consists of a color-dominant branch and a depth-dominant branch to exploit and fuse two modalities thoroughly. More specifically, one branch inputs a color image and a sparse depth map to predict a dense depth map. The other branch takes as inputs the sparse depth map and the previously predicted depth map, and outputs a dense depth map as well. The depth maps predicted from two branches are complimentary to each other and therefore they are adaptively fused. In addition, we also propose a simple geometric convolutional layer to encode 3D geometric cues. The geometric encoded backbone conducts the fusion of different modalities at multiple stages, leading to good depth completion results. We further implement a dilated and accelerated CSPN++ to refine the fused depth map efficiently. The proposed full model ranks 1st in the KITTI depth completion online leaderboard at the time of submission. It also infers much faster than most of the top ranked methods. The code of this work is available at https://github.com/JUGGHM/PENet_ICRA2021.

Bin Li, Ye Shi, Qian Yu et al.

Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images sharing the same category across diverse domains without relying on labeled data. Prior approaches have typically decomposed the UCIR problem into two distinct tasks: intra-domain representation learning and cross-domain feature alignment. However, these segregated strategies overlook the potential synergies between these tasks. This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework. ProtoOT leverages the strengths of the K-means clustering method to effectively manage distribution imbalances inherent in UCIR. By utilizing K-means for generating initial prototypes and approximating class marginal distributions, we modify the constraints in Optimal Transport accordingly, significantly enhancing its performance in UCIR scenarios. Furthermore, we incorporate contrastive learning into the ProtoOT framework to further improve representation learning. This encourages local semantic consistency among features with similar semantics, while also explicitly enforcing separation between features and unmatched prototypes, thereby enhancing global discriminativeness. ProtoOT surpasses existing state-of-the-art methods by a notable margin across benchmark datasets. Notably, on DomainNet, ProtoOT achieves an average P@200 enhancement of 18.17%, and on Office-Home, it demonstrates a P@15 improvement of 3.83%.

Qitan Lv, Jie Wang, Hanzhu Chen et al.

Generation of plausible but incorrect factual information, often termed hallucination, has attracted significant research interest. Retrieval-augmented language model (RALM) -- which enhances models with up-to-date knowledge -- emerges as a promising method to reduce hallucination. However, existing RALMs may instead exacerbate hallucination when retrieving lengthy contexts. To address this challenge, we propose COFT, a novel \textbf{CO}arse-to-\textbf{F}ine highligh\textbf{T}ing method to focus on different granularity-level key texts, thereby avoiding getting lost in lengthy contexts. Specifically, COFT consists of three components: \textit{recaller}, \textit{scorer}, and \textit{selector}. First, \textit{recaller} applies a knowledge graph to extract potential key entities in a given context. Second, \textit{scorer} measures the importance of each entity by calculating its contextual weight. Finally, \textit{selector} selects high contextual weight entities with a dynamic threshold algorithm and highlights the corresponding paragraphs, sentences, or words in a coarse-to-fine manner. Extensive experiments on the knowledge hallucination benchmark demonstrate the effectiveness of COFT, leading to a superior performance over $30\%$ in the F1 score metric. Moreover, COFT also exhibits remarkable versatility across various long-form tasks, such as reading comprehension and question answering.

Haiyang Yu, Xiaocong Wang, Bin Li et al.

Scene text recognition (STR) has attracted much attention due to its broad applications. The previous works pay more attention to dealing with the recognition of Latin text images with complex backgrounds by introducing language models or other auxiliary networks. Different from Latin texts, many vertical Chinese texts exist in natural scenes, which brings difficulties to current state-of-the-art STR methods. In this paper, we take the first attempt to extract orientation-independent visual features by disentangling content and orientation information of text images, thus recognizing both horizontal and vertical texts robustly in natural scenes. Specifically, we introduce a Character Image Reconstruction Network (CIRN) to recover corresponding printed character images with disentangled content and orientation information. We conduct experiments on a scene dataset for benchmarking Chinese text recognition, and the results demonstrate that the proposed method can indeed improve performance through disentangling content and orientation information. To further validate the effectiveness of our method, we additionally collect a Vertical Chinese Text Recognition (VCTR) dataset. The experimental results show that the proposed method achieves 45.63% improvement on VCTR when introducing CIRN to the baseline model.

Bin Li, Hanjun Deng

Generating personalized responses is one of the major challenges in natural human-robot interaction. Current researches in this field mainly focus on generating responses consistent with the robot's pre-assigned persona, while ignoring the user's persona. Such responses may be inappropriate or even offensive, which may lead to the bad user experience. Therefore, we propose a Bilateral Personalized Dialogue Generation (BPDG) method for dyadic conversation, which integrates user and robot personas into dialogue generation via designing a dynamic persona-aware fusion method. To bridge the gap between the learning objective function and evaluation metrics, the Conditional Mutual Information Maximum (CMIM) criterion is adopted with contrastive learning to select the proper response from the generated candidates. Moreover, a bilateral persona accuracy metric is designed to measure the degree of bilateral personalization. Experimental results demonstrate that, compared with several state-of-the-art methods, the final results of the proposed method are more personalized and consistent with bilateral personas in terms of both automatic and manual evaluations.

Bin Li, Panpan Zhang, Jinye Peng et al.

Heartbeat rhythm and heart rate (HR) are important physiological parameters of the human body. This study presents an efficient multi-hierarchical spatio-temporal convolutional network that can quickly estimate remote physiological (rPPG) signal and HR from face video clips. First, the facial color distribution characteristics are extracted using a low-level face feature generation (LFFG) module. Then, the three-dimensional (3D) spatio-temporal stack convolution module (STSC) and multi-hierarchical feature fusion module (MHFF) are used to strengthen the spatio-temporal correlation of multi-channel features. In the MHFF, sparse optical flow is used to capture the tiny motion information of faces between frames and generate a self-adaptive region of interest (ROI) skin mask. Finally, the signal prediction module (SP) is used to extract the estimated rPPG signal. The heart rate estimation results show that the proposed network overperforms the state-of-the-art methods on three datasets, 1) UBFC-RPPG, 2) COHFACE, 3) our dataset, with the mean absolute error (MAE) of 2.15, 5.57, 1.75 beats per minute (bpm) respectively.

Bin Li, Hong Fu, Ruimin Li et al.

Accurate hand joints detection from images is a fundamental topic which is essential for many applications in computer vision and human computer interaction. This paper presents a two stage network for hand joints detection from single unmarked image by using serial-parallel multi-scale feature fusion. In stage I, the hand regions are located by a pre-trained network, and the features of each detected hand region are extracted by a shallow spatial hand features representation module. The extracted hand features are then fed into stage II, which consists of serially connected feature extraction modules with similar structures, called "multi-scale feature fusion" (MSFF). A MSFF contains parallel multi-scale feature extraction branches, which generate initial hand joint heatmaps. The initial heatmaps are then mutually reinforced by the anatomic relationship between hand joints. The experimental results on five hand joints datasets show that the proposed network overperforms the state-of-the-art methods.