Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) stand as the two most popular foundation models for visual representation learning. While CNNs exhibit remarkable scalability with linear complexity w.r.t. image resolution, ViTs surpass them in fitting capabilities despite contending with quadratic complexity. A closer inspection reveals that ViTs achieve superior visual modeling performance through the incorporation of global receptive fields and dynamic weights. This observation motivates us to propose a novel architecture that inherits these components while enhancing computational efficiency. To this end, we draw inspiration from the recently introduced state space model and propose the Visual State Space Model (VMamba), which achieves linear complexity without sacrificing global receptive fields. To address the encountered direction-sensitive issue, we introduce the Cross-Scan Module (CSM) to traverse the spatial domain and convert any non-causal visual image into order patch sequences. Extensive experimental results substantiate that VMamba not only demonstrates promising capabilities across various visual perception tasks, but also exhibits more pronounced advantages over established benchmarks as the image resolution increases. Source code has been available at https://github.com/MzeroMiko/VMamba.
Multi-view compression technology, especially Stereo Image Compression (SIC), plays a crucial role in car-mounted cameras and 3D-related applications. Interestingly, the Distributed Source Coding (DSC) theory suggests that efficient data compression of correlated sources can be achieved through independent encoding and joint decoding. This motivates the rapidly developed deep-distributed SIC methods in recent years. However, these approaches neglect the unique characteristics of stereo-imaging tasks and incur high decoding latency. To address this limitation, we propose a Feature-based Fast Cascade Alignment network (FFCA-Net) to fully leverage the side information on the decoder. FFCA adopts a coarse-to-fine cascaded alignment approach. In the initial stage, FFCA utilizes a feature domain patch-matching module based on stereo priors. This module reduces redundancy in the search space of trivial matching methods and further mitigates the introduction of noise. In the subsequent stage, we utilize an hourglass-based sparse stereo refinement network to further align inter-image features with a reduced computational cost. Furthermore, we have devised a lightweight yet high-performance feature fusion network, called a Fast Feature Fusion network (FFF), to decode the aligned features. Experimental results on InStereo2K, KITTI, and Cityscapes datasets demonstrate the significant superiority of our approach over traditional and learning-based SIC methods. In particular, our approach achieves significant gains in terms of 3 to 10-fold faster decoding speed than other methods.
Crowd counting has achieved significant progress by training regressors to predict instance positions. In heavily crowded scenarios, however, regressors are challenged by uncontrollable annotation variance, which causes density map bias and context information inaccuracy. In this study, we propose mutual prompt learning (mPrompt), which leverages a regressor and a segmenter as guidance for each other, solving bias and inaccuracy caused by annotation variance while distinguishing foreground from background. In specific, mPrompt leverages point annotations to tune the segmenter and predict pseudo head masks in a way of point prompt learning. It then uses the predicted segmentation masks, which serve as spatial constraint, to rectify biased point annotations as context prompt learning. mPrompt defines a way of mutual information maximization from prompt learning, mitigating the impact of annotation variance while improving model accuracy. Experiments show that mPrompt significantly reduces the Mean Average Error (MAE), demonstrating the potential to be general framework for down-stream vision tasks.
The study of causal relationships between emotions and causes in texts has recently received much attention. Most works focus on extracting causally related clauses from documents. However, none of these works has considered that the causal relationships among the extracted emotion and cause clauses can only be valid under some specific context clauses. To highlight the context in such special causal relationships, we propose a new task to determine whether or not an input pair of emotion and cause has a valid causal relationship under different contexts and extract the specific context clauses that participate in the causal relationship. Since the task is new for which no existing dataset is available, we conduct manual annotation on a benchmark dataset to obtain the labels for our tasks and the annotations of each context clause's type that can also be used in some other applications. We adopt negative sampling to construct the final dataset to balance the number of documents with and without causal relationships. Based on the constructed dataset, we propose an end-to-end multi-task framework, where we design two novel and general modules to handle the two goals of our task. Specifically, we propose a context masking module to extract the context clauses participating in the causal relationships. We propose a prediction aggregation module to fine-tune the prediction results according to whether the input emotion and causes depend on specific context clauses. Results of extensive comparative experiments and ablation studies demonstrate the effectiveness and generality of our proposed framework.
In contrast to conventional visual question answering, video-grounded dialog necessitates a profound understanding of both dialog history and video content for accurate response generation. Despite commendable strides made by existing methodologies, they often grapple with the challenges of incrementally understanding intricate dialog histories and assimilating video information. In response to this gap, we present an iterative tracking and reasoning strategy that amalgamates a textual encoder, a visual encoder, and a generator. At its core, our textual encoder is fortified with a path tracking and aggregation mechanism, adept at gleaning nuances from dialog history that are pivotal to deciphering the posed questions. Concurrently, our visual encoder harnesses an iterative reasoning network, meticulously crafted to distill and emphasize critical visual markers from videos, enhancing the depth of visual comprehension. Culminating this enriched information, we employ the pre-trained GPT-2 model as our response generator, stitching together coherent and contextually apt answers. Our empirical assessments, conducted on two renowned datasets, testify to the prowess and adaptability of our proposed design.
Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify them. To maintain the CLIP's zero-shot transferability, previous practices favour to freeze CLIP during training. However, in the paper, we reveal that CLIP is insensitive to different mask proposals and tends to produce similar predictions for various mask proposals of the same image. This insensitivity results in numerous false positives when classifying mask proposals. This issue mainly relates to the fact that CLIP is trained with image-level supervision. To alleviate this issue, we propose a simple yet effective method, named Mask-aware Fine-tuning (MAFT). Specifically, Image-Proposals CLIP Encoder (IP-CLIP Encoder) is proposed to handle arbitrary numbers of image and mask proposals simultaneously. Then, mask-aware loss and self-distillation loss are designed to fine-tune IP-CLIP Encoder, ensuring CLIP is responsive to different mask proposals while not sacrificing transferability. In this way, mask-aware representations can be easily learned to make the true positives stand out. Notably, our solution can seamlessly plug into most existing methods without introducing any new parameters during the fine-tuning process. We conduct extensive experiments on the popular zero-shot benchmarks. With MAFT, the performance of the state-of-the-art methods is promoted by a large margin: 50.4% (+ 8.2%) on COCO, 81.8% (+ 3.2%) on Pascal-VOC, and 8.7% (+4.3%) on ADE20K in terms of mIoU for unseen classes. The code is available at https://github.com/jiaosiyu1999/MAFT.git.
Text-based Person Retrieval aims to retrieve the target person images given a textual query. The primary challenge lies in bridging the substantial gap between vision and language modalities, especially when dealing with limited large-scale datasets. In this paper, we introduce a CLIP-based Synergistic Knowledge Transfer(CSKT) approach for TBPR. Specifically, to explore the CLIP's knowledge on input side, we first propose a Bidirectional Prompts Transferring (BPT) module constructed by text-to-image and image-to-text bidirectional prompts and coupling projections. Secondly, Dual Adapters Transferring (DAT) is designed to transfer knowledge on output side of Multi-Head Self-Attention (MHSA) in vision and language. This synergistic two-way collaborative mechanism promotes the early-stage feature fusion and efficiently exploits the existing knowledge of CLIP. CSKT outperforms the state-of-the-art approaches across three benchmark datasets when the training parameters merely account for 7.4% of the entire model, demonstrating its remarkable efficiency, effectiveness and generalization.
Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is time-consuming and expensive for many scenarios and languages. Therefore, sufficient labeled pairs are usually not available. To deal with the label shortage problem, we present a simple yet effective zero-shot approach MultiCapCLIP that can generate visual captions for different scenarios and languages without any labeled vision-caption pairs of downstream datasets. In the training stage, MultiCapCLIP only requires text data for input. Then it conducts two main steps: 1) retrieving concept prompts that preserve the corresponding domain knowledge of new scenarios; 2) auto-encoding the prompts to learn writing styles to output captions in a desired language. In the testing stage, MultiCapCLIP instead takes visual data as input directly to retrieve the concept prompts to generate the final visual descriptions. The extensive experiments on image and video captioning across four benchmarks and four languages (i.e., English, Chinese, German, and French) confirm the effectiveness of our approach. Compared with state-of-the-art zero-shot and weakly-supervised methods, our method achieves 4.8% and 21.5% absolute improvements in terms of BLEU@4 and CIDEr metrics. Our code is available at https://github.com/yangbang18/MultiCapCLIP.
Existing visual tracking methods typically take an image patch as the reference of the target to perform tracking. However, a single image patch cannot provide a complete and precise concept of the target object as images are limited in their ability to abstract and can be ambiguous, which makes it difficult to track targets with drastic variations. In this paper, we propose the CiteTracker to enhance target modeling and inference in visual tracking by connecting images and text. Specifically, we develop a text generation module to convert the target image patch into a descriptive text containing its class and attribute information, providing a comprehensive reference point for the target. In addition, a dynamic description module is designed to adapt to target variations for more effective target representation. We then associate the target description and the search image using an attention-based correlation module to generate the correlated features for target state reference. Extensive experiments on five diverse datasets are conducted to evaluate the proposed algorithm and the favorable performance against the state-of-the-art methods demonstrates the effectiveness of the proposed tracking method.
The exponential growth of data, alongside advancements in model structures and loss functions, has necessitated the enhancement of image retrieval systems through the utilization of new models with superior feature embeddings. However, the expensive process of updating the old retrieval database by replacing embeddings poses a challenge. As a solution, backward-compatible training can be employed to avoid the necessity of updating old retrieval datasets. While previous methods achieved backward compatibility by aligning prototypes of the old model, they often overlooked the distribution of the old features, thus limiting their effectiveness when the old model's low quality leads to a weakly discriminative feature distribution. On the other hand, instance-based methods like L2 regression take into account the distribution of old features but impose strong constraints on the performance of the new model itself. In this paper, we propose MixBCT, a simple yet highly effective backward-compatible training method that serves as a unified framework for old models of varying qualities. Specifically, we summarize four constraints that are essential for ensuring backward compatibility in an ideal scenario, and we construct a single loss function to facilitate backward-compatible training. Our approach adaptively adjusts the constraint domain for new features based on the distribution of the old embeddings. We conducted extensive experiments on the large-scale face recognition datasets MS1Mv3 and IJB-C to verify the effectiveness of our method. The experimental results clearly demonstrate its superiority over previous methods. Code is available at https://github.com/yuleung/MixBCT