In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized data can be infinite in theory, the scientific conundrum persists that how much generated data optimally fuels subsequent model training. We observe that only a subset of the data in these constructed datasets plays a decisive role. Therefore, we introduce a new Filtering-WoRA paradigm, which contains a filtering algorithm to identify this crucial data subset and WoRA (Weighted Low-Rank Adaptation) learning strategy for light fine-tuning. The filtering algorithm is based on the cross-modality relevance to remove the lots of coarse matching synthesis pairs. As the number of data decreases, we do not need to fine-tune the entire model. Therefore, we propose a WoRA learning strategy to efficiently update a minimal portion of model parameters. WoRA streamlines the learning process, enabling heightened efficiency in extracting knowledge from fewer, yet potent, data instances. Extensive experimentation validates the efficacy of pretraining, where our model achieves advanced and efficient retrieval performance on challenging real-world benchmarks. Notably, on the CUHK-PEDES dataset, we have achieved a competitive mAP of 67.02% while reducing model training time by 19.82%.
In this paper, we study the text-guided image generation task. Our focus lies in the modification of a reference image, given user text feedback, to imbue it with specific desired properties. Despite recent strides in this field, a persistent challenge remains that single-round optimization often overlooks crucial details, particularly in the realm of fine-grained changes like shoes or sleeves. This misalignment accumulation significantly hampers multi-round customization during interaction. In an attempt to address this challenge, we introduce a new self-supervised regularization into the existing framework, i.e., multi-round regularization. It builds upon the observation that the modification order does not affect the final result. As the name suggests, the multi-round regularization encourages the model to maintain consistency across different modification orders. Specifically, our proposed approach addresses the issue where an initial failure to capture fine-grained details leads to substantial discrepancies after multiple rounds, as opposed to traditional one-round learning. Both qualitative and quantitative experiments show the proposed method achieves high-fidelity generation quality over the text-guided generation task, especially the local modification. Furthermore, we extend the evaluation to semantic alignment with text by applying our method to text-guided retrieval datasets, such as FahisonIQ, where it demonstrates competitive performance.
Drone navigation through natural language commands remains a significant challenge due to the lack of publicly available multi-modal datasets and the intricate demands of fine-grained visual-text alignment. In response to this pressing need, we present a new human-computer interaction annotation benchmark called GeoText-1652, meticulously curated through a robust Large Language Model (LLM)-based data generation framework and the expertise of pre-trained vision models. This new dataset seamlessly extends the existing image dataset, \ie, University-1652, with spatial-aware text annotations, encompassing intricate image-text-bounding box associations. Besides, we introduce a new optimization objective to leverage fine-grained spatial associations, called blending spatial matching, for region-level spatial relation matching. Extensive experiments reveal that our approach maintains an exceptional recall rate under varying description complexities. This underscores the promising potential of our approach in elevating drone control and navigation through the seamless integration of natural language commands in real-world scenarios.
Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations in the target domain. To facilitate domain-invariant feature learning, existing methods typically mix data from both the source domain and target domain by simply copying and pasting the pixels. Such vanilla methods are usually sub-optimal since they do not take into account how well the mixed layouts correspond to real-world scenarios. Real-world scenarios are with an inherent layout. We observe that semantic categories, such as sidewalks, buildings, and sky, display relatively consistent depth distributions, and could be clearly distinguished in a depth map. Based on such observation, we propose a depth-aware framework to explicitly leverage depth estimation to mix the categories and facilitate the two complementary tasks, i.e., segmentation and depth learning in an end-to-end manner. In particular, the framework contains a Depth-guided Contextual Filter (DCF) forndata augmentation and a cross-task encoder for contextual learning. DCF simulates the real-world layouts, while the cross-task encoder further adaptively fuses the complementing features between two tasks. Besides, it is worth noting that several public datasets do not provide depth annotation. Therefore, we leverage the off-the-shelf depth estimation network to generate the pseudo depth. Extensive experiments show that our proposed methods, even with pseudo depth, achieve competitive performance on two widely-used bench-marks, i.e. 77.7 mIoU on GTA to Cityscapes and 69.3 mIoU on Synthia to Cityscapes.
Text-to-3D generation is to craft a 3D object according to a natural language description. This can significantly reduce the workload for manually designing 3D models and provide a more natural way of interaction for users. However, this problem remains challenging in recovering the fine-grained details effectively and optimizing a large-size 3D output efficiently. Inspired by the success of progressive learning, we propose a Multi-Scale Triplane Network (MTN) and a new progressive learning strategy. As the name implies, the Multi-Scale Triplane Network consists of four triplanes transitioning from low to high resolution. The low-resolution triplane could serve as an initial shape for the high-resolution ones, easing the optimization difficulty. To further enable the fine-grained details, we also introduce the progressive learning strategy, which explicitly demands the network to shift its focus of attention from simple coarse-grained patterns to difficult fine-grained patterns. Our experiment verifies that the proposed method performs favorably against existing methods. For even the most challenging descriptions, where most existing methods struggle to produce a viable shape, our proposed method consistently delivers. We aspire for our work to pave the way for automatic 3D prototyping via natural language descriptions.
In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and image-text matching tasks in one stone. In particular, MALS contains 1,510,330 image-text pairs, which is about 37.5 times larger than prevailing CUHK-PEDES, and all images are annotated with 27 attributes. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text. As the name implies, APTM contains an attribute prompt learning stream and a text matching learning stream. (1) The attribute prompt learning leverages the attribute prompts for image-attribute alignment, which enhances the text matching learning. (2) The text matching learning facilitates the representation learning on fine-grained details, and in turn, boosts the attribute prompt learning. Extensive experiments validate the effectiveness of the pre-training on MALS, achieving state-of-the-art retrieval performance via APTM on three challenging real-world benchmarks. In particular, APTM achieves a consistent improvement of +6.60%, +7.39%, and +15.90% Recall@1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets by a clear margin, respectively.
Language-guided image retrieval enables users to search for images and interact with the retrieval system more naturally and expressively by using a reference image and a relative caption as a query. Most existing studies mainly focus on designing image-text composition architecture to extract discriminative visual-linguistic relations. Despite great success, we identify an inherent problem that obstructs the extraction of discriminative features and considerably compromises model training: \textbf{triplet ambiguity}. This problem stems from the annotation process wherein annotators view only one triplet at a time. As a result, they often describe simple attributes, such as color, while neglecting fine-grained details like location and style. This leads to multiple false-negative candidates matching the same modification text. We propose a novel Consensus Network (Css-Net) that self-adaptively learns from noisy triplets to minimize the negative effects of triplet ambiguity. Inspired by the psychological finding that groups perform better than individuals, Css-Net comprises 1) a consensus module featuring four distinct compositors that generate diverse fused image-text embeddings and 2) a Kullback-Leibler divergence loss, which fosters learning among the compositors, enabling them to reduce biases learned from noisy triplets and reach a consensus. The decisions from four compositors are weighted during evaluation to further achieve consensus. Comprehensive experiments on three datasets demonstrate that Css-Net can alleviate triplet ambiguity, achieving competitive performance on benchmarks, such as $+2.77\%$ R@10 and $+6.67\%$ R@50 on FashionIQ.
Existing task-oriented conversational search systems heavily rely on domain ontologies with pre-defined slots and candidate value sets. In practical applications, these prerequisites are hard to meet, due to the emerging new user requirements and ever-changing scenarios. To mitigate these issues for better interaction performance, there are efforts working towards detecting out-of-vocabulary values or discovering new slots under unsupervised or semi-supervised learning paradigm. However, overemphasizing on the conversation data patterns alone induces these methods to yield noisy and arbitrary slot results. To facilitate the pragmatic utility, real-world systems tend to provide a stringent amount of human labelling quota, which offers an authoritative way to obtain accurate and meaningful slot assignments. Nonetheless, it also brings forward the high requirement of utilizing such quota efficiently. Hence, we formulate a general new slot discovery task in an information extraction fashion and incorporate it into an active learning framework to realize human-in-the-loop learning. Specifically, we leverage existing language tools to extract value candidates where the corresponding labels are further leveraged as weak supervision signals. Based on these, we propose a bi-criteria selection scheme which incorporates two major strategies, namely, uncertainty-based sampling and diversity-based sampling to efficiently identify terms of interest. We conduct extensive experiments on several public datasets and compare with a bunch of competitive baselines to demonstrate the effectiveness of our method. We have made the code and data used in this paper publicly available.
Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the higher-order neighbor relations (i.e., a matching structure among multiple data samples). Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. However, it is ineffective to directly extend existing re-ranking algorithms to image-text retrieval. In this paper, we analyze the reason from four perspectives, i.e., generalization, flexibility, sparsity, and asymmetry, and propose a novel learnable pillar-based re-ranking paradigm. Concretely, we first select top-ranked intra- and inter-modal neighbors as pillars, and then reconstruct data samples with the neighbor relations between them and the pillars. In this way, each sample can be mapped into a multimodal pillar space only using similarities, ensuring generalization. After that, we design a neighbor-aware graph reasoning module to flexibly exploit the relations and excavate the sparse positive items within a neighborhood. We also present a structure alignment constraint to promote cross-modal collaboration and align the asymmetric modalities. On top of various base backbones, we carry out extensive experiments on two benchmark datasets, i.e., Flickr30K and MS-COCO, demonstrating the effectiveness, superiority, generalization, and transferability of our proposed re-ranking paradigm.
Sign language recognition (SLR) aims to overcome the communication barrier for the people with deafness or the people with hard hearing. Most existing approaches can be typically divided into two lines, i.e., Skeleton-based and RGB-based methods, but both the two lines of methods have their limitations. RGB-based approaches usually overlook the fine-grained hand structure, while Skeleton-based methods do not take the facial expression into account. In attempts to address both limitations, we propose a new framework named Spatial-temporal Part-aware network (StepNet), based on RGB parts. As the name implies, StepNet consists of two modules: Part-level Spatial Modeling and Part-level Temporal Modeling. Particularly, without using any keypoint-level annotations, Part-level Spatial Modeling implicitly captures the appearance-based properties, such as hands and faces, in the feature space. On the other hand, Part-level Temporal Modeling captures the pertinent properties over time by implicitly mining the long-short term context. Extensive experiments show that our StepNet, thanks to Spatial-temporal modules, achieves competitive Top-1 Per-instance accuracy on three widely-used SLR benchmarks, i.e., 56.89% on WLASL, 77.2% on NMFs-CSL, and 77.1% on BOBSL. Moreover, the proposed method is compatible with the optical flow input, and can yield higher performance if fused. We hope that this work can serve as a preliminary step for the people with deafness.